INDEX

Explanations

mentions of criminal or morally reprehensible activities

oai_token-act-pair · gpt-3.5-turbo

words and phrases related to legal and social violations

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

 UNCLASSIFIED

-0.85

anwhile

-0.80

pse

-0.72

)."

-0.69

 Azerb

-0.69

.).

-0.69

é¾įå

-0.66

âķĲ

-0.65

âĹ¼

-0.62

 thereafter

-0.61

POSITIVE LOGITS

 Belfast

0.81

 âĢº

0.74

 âĢİ

0.62

âĢİ

0.59

 Copyright

0.56

 Posted

0.56

Skip

0.54

 cryptocurrency

0.53

 Donald

0.53

 lately

0.52

Activations Density 1.853%

mentions of criminal or morally reprehensible activities

words and phrases related to legal and social violations

No Comments

No Known Activations