INDEX

Explanations

sensitive issues or controversy in a text

oai_token-act-pair · gpt-3.5-turbo

indicators of significant issues or warnings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

etheless

-0.87

hement

-0.83

 unprotected

-0.81

 scrap

-0.71

 endeav

-0.71

 indu

-0.70

 succumb

-0.69

 streng

-0.68

 afloat

-0.67

 conscious

-0.67

POSITIVE LOGITS

Newsletter

0.97

Loading

0.97

Wilson

0.96

Said

0.95

Official

0.94

Posted

0.93

SPONSORED

0.90

Comment

0.90

Anonymous

0.88

Trivia

0.87

Activations Density 0.197%

sensitive issues or controversy in a text

indicators of significant issues or warnings

No Comments

No Known Activations