INDEX

Explanations

insulting or critical phrases

oai_token-act-pair · gpt-3.5-turbo

words related to negative criticisms and societal issues

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

minster

-0.67

Newsletter

-0.66

 Downs

-0.64

holm

-0.62

kaya

-0.61

Äĩ

-0.60

boro

-0.60

hover

-0.60

rav

-0.60

wake

-0.59

POSITIVE LOGITS

lished

0.70

ciating

0.63

 lett

0.62

ļéĨĴ

0.61

 Geek

0.57

 metic

0.57

essors

0.57

UNC

0.53

 hybrids

0.52

estyles

0.51

Activations Density 0.534%

insulting or critical phrases

words related to negative criticisms and societal issues

No Comments

No Known Activations