INDEX

Explanations

mentions of reviews

oai_token-act-pair · gpt-3.5-turbo

mentions of reviews and ratings

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

chest

-0.73

llular

-0.70

nown

-0.68

fw

-0.68

bodied

-0.67

riminal

-0.63

 NOTICE

-0.62

SPONSORED

-0.61

iak

-0.61

NetMessage

-0.61

POSITIVE LOGITS

Reviewed

1.07

 Reviews

1.03

 reviews

0.96

 reviewer

0.87

Review

0.85

 reviewers

0.79

 review

0.78

 essays

0.76

 endorsements

0.72

 ratings

0.71

Activations Density 0.037%

mentions of reviews

mentions of reviews and ratings

No Comments

No Known Activations