INDEX

Explanations

company or product names

oai_token-act-pair · gpt-3.5-turbo

instances of the word "Anonymous" and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

eele

-0.82

lasses

-0.75

ombo

-0.74

grain

-0.73

 Gork

-0.73

rums

-0.72

ushing

-0.71

matically

-0.68

dropping

-0.67

inson

-0.66

POSITIVE LOGITS

News

0.80

Party

0.80

 Anonymous

0.76

 hacker

0.76

Wiki

0.71

Anonymous

0.70

username

0.70

Members

0.69

 hackers

0.68

 Hacker

0.66

Activations Density 0.042%

company or product names

instances of the word "Anonymous" and related terms

No Comments

No Known Activations