INDEX

Explanations

comparisons between different entities or concepts

oai_token-act-pair · gpt-3.5-turbo

phrases related to contrasting situations or viewpoints

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 Windsor

-0.65

SPA

-0.61

 highs

-0.61

 doors

-0.59

WARD

-0.59

 Waterloo

-0.57

 Marketplace

-0.57

 Astral

-0.57

 foreigner

-0.57

zn

-0.56

POSITIVE LOGITS

 fared

0.89

 thri

0.88

 denies

0.87

udes

0.81

 owes

0.80

 withdrew

0.80

 retains

0.79

 suffers

0.79

 reacted

0.79

 accommod

0.78

Activations Density 0.156%

comparisons between different entities or concepts

phrases related to contrasting situations or viewpoints

No Comments

No Known Activations