INDEX

Explanations

disclaimers and statements indicating that opinions expressed are not necessarily those of a larger entity

oai_token-act-pair · gpt-3.5-turbo

statements of caution or disclaimers regarding opinions expressed by individuals or participants

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

 taps

-0.73

milo

-0.73

aunts

-0.73

ghazi

-0.71

 manifold

-0.67

chio

-0.66

gered

-0.66

INTON

-0.65

Mot

-0.62

 Sabha

-0.62

POSITIVE LOGITS

 disclaimer

0.96

 disclaim

0.89

 editorial

0.88

 copyright

0.86

 trademark

0.84

 trademarks

0.84

 copyrighted

0.83

 strictly

0.81

 privacy

0.80

 NOTICE

0.80

Activations Density 0.768%

disclaimers and statements indicating that opinions expressed are not necessarily those of a larger entity

statements of caution or disclaimers regarding opinions expressed by individuals or participants

No Comments

No Known Activations