INDEX

Explanations

descriptive or explanatory terms and phrases

oai_token-act-pair · gpt-3.5-turbo

significant abstract concepts and terms related to arguments or discussions

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

ilver

-0.59

iolet

-0.58

incinn

-0.58

vae

-0.56

asketball

-0.54

poon

-0.53

akia

-0.53

isine

-0.53

hma

-0.52

Lago

-0.52

POSITIVE LOGITS

iest

0.92

liest

0.86

natureconservancy

0.74

of

0.73

 itself

0.70

ultimate

0.65

 portion

0.64

 thereof

0.61

 aspect

0.59

 keyword

0.58

Activations Density 0.585%

descriptive or explanatory terms and phrases

significant abstract concepts and terms related to arguments or discussions

No Comments

No Known Activations