INDEX

Explanations

Commas used to introduce additional information, often following a conjunction or preceding a quote, particularly in complex sentences discussing social, political, or cultural topics.

eleuther_acts_top20 · claude-3-5-sonnet-20240620 Triggered by @jake

Explanation could not be parsed.

eleuther_acts_top20 · o3-mini Triggered by @jake

Explanation could not be parsed.

eleuther_acts_top20 · deepseek-r1 Triggered by @jake

The token "," before "because" in sentences, connecting clauses or expanding reasoning.

eleuther_acts_top20 · deepseek-v3 Triggered by @jake

sentences containing em dashes (—) or hyphens (-) separating clauses or phrases, indicating pauses or additional information.

oai_token-act-pair · deepseek-v3 Triggered by @jake

descriptions related to criminal activities and law enforcement

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs6144-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_6144

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

6,144

Data Type

torch.float32

Hook Point

blocks.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

olves

-0.81

SourceFile

-0.73

aukee

-0.68

zing

-0.66

 Coverage

-0.64

ÅĤ

-0.63

nexus

-0.62

igers

-0.60

externalActionCode

-0.59

cium

-0.59

POSITIVE LOGITS

 alas

1.20

 interestingly

0.98

 moreover

0.96

 unlike

0.96

 unsurprisingly

0.96

 contrary

0.94

 although

0.94

 according

0.92

 despite

0.92

 unfortunately

0.90

Activations Density 0.314%

Commas used to introduce additional information, often following a conjunction or preceding a quote, particularly in complex sentences discussing social, political, or cultural topics.

Explanation could not be parsed.

Explanation could not be parsed.

The token "," before "because" in sentences, connecting clauses or expanding reasoning.

sentences containing em dashes (—) or hyphens (-) separating clauses or phrases, indicating pauses or additional information.

descriptions related to criminal activities and law enforcement

No Comments

No Known Activations