INDEX

Explanations

titles, names, and proper nouns

oai_token-act-pair · gpt-3.5-turbo

references to specific people or concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

Foot

-0.66

byter

-0.65

iter

-0.64

rely

-0.63

olas

-0.61

itary

-0.59

ionic

-0.59

obbies

-0.58

 comprom

-0.57

paces

-0.56

POSITIVE LOGITS

,,,,,,,,

0.89

,,,,

0.81

taboola

0.81

tel

0.80

::::::::

0.78

::::

0.75

then

0.73

tra

0.73

 Canary

0.72

pee

0.71

Activations Density 0.037%

titles, names, and proper nouns

references to specific people or concepts

No Comments

No Known Activations