INDEX

Explanations

words or names beginning with "Oc" or "O" followed by another consonant, particularly in proper nouns or names.

oai_token-act-pair · claude-3-5-sonnet-20240620 Triggered by @danielepoterti

names and organizations related to politics and activism

oai_token-act-pair · gpt-3.5-turbo

proper nouns, specifically names and locations

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

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

channelAvailability

-0.60

 confines

-0.60

CPC

-0.58

 separat

-0.58

 goats

-0.56

bourg

-0.56

 STATS

-0.55

SHIP

-0.55

htar

-0.53

BIP

-0.53

POSITIVE LOGITS

Wan

0.85

leck

0.82

worldly

0.77

orio

0.76

actory

0.75

ratulations

0.74

wald

0.72

yssey

0.70

acan

0.69

uary

0.69

Activations Density 0.090%

words or names beginning with "Oc" or "O" followed by another consonant, particularly in proper nouns or names.

names and organizations related to politics and activism

proper nouns, specifically names and locations

No Comments

No Known Activations