INDEX

Explanations

mentions of individuals or entities involved in conflicts or controversies

oai_token-act-pair · gpt-3.5-turbo

references to political figures and their criticisms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

aceae

-0.80

staking

-0.80

 largeDownload

-0.63

 prest

-0.61

 seism

-0.61

Sie

-0.58

 Cind

-0.58

Ded

-0.57

 shortest

-0.57

VILLE

-0.56

POSITIVE LOGITS

 inaction

0.98

 hypocrisy

0.92

 injust

0.91

 policies

0.89

 bigotry

0.88

 evils

0.87

 injustice

0.87

 racism

0.85

 encro

0.85

 prejudice

0.83

Activations Density 0.613%

mentions of individuals or entities involved in conflicts or controversies

references to political figures and their criticisms

No Comments

No Known Activations