INDEX

Explanations

pronouns and identity-related words

oai_token-act-pair · gpt-3.5-turbo

references to personal identity and relationships

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

assembly

-0.58

 Round

-0.57

 Shelby

-0.56

entary

-0.55

atory

-0.54

 Associated

-0.53

atel

-0.52

 Gene

-0.52

 Nationwide

-0.52

 Millennium

-0.51

POSITIVE LOGITS

'll

1.06

've

1.04

'd

0.98

're

0.89

owe

0.84

 reluct

0.81

 encount

0.80

 knew

0.78

ATHER

0.75

 swore

0.71

Activations Density 0.599%

pronouns and identity-related words

references to personal identity and relationships

No Comments

No Known Activations