INDEX

Explanations

verbs or nouns related to a downward or negative trend

oai_token-act-pair · gpt-3.5-turbo

present participles and gerunds, particularly those indicating ongoing actions or processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

ufact

-1.02

vironment

-0.64

etimes

-0.63

ilies

-0.62

iston

-0.62

 pulp

-0.61

unts

-0.61

ccess

-0.61

PLIC

-0.60

 sust

-0.59

POSITIVE LOGITS

peed

0.88

adia

0.83

cycles

0.82

abouts

0.80

cffffcc

0.79

shaped

0.79

agonal

0.75

adesh

0.75

 downwards

0.74

 hither

0.73

Activations Density 0.149%

verbs or nouns related to a downward or negative trend

present participles and gerunds, particularly those indicating ongoing actions or processes

No Comments

No Known Activations