INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

£ı

-0.78

ļéĨĴ

-0.77

ovember

-0.76

gravity

-0.75

 Flavoring

-0.73

Ã¸

-0.71

nesota

-0.70

ethyl

-0.69

culus

-0.69

mson

-0.69

POSITIVE LOGITS

 arte

0.65

Browser

0.62

 overwrite

0.59

 click

0.58

Sem

0.57

Buk

0.57

 lightning

0.56

 imag

0.56

nud

0.56

 refresh

0.55

Activations Density 0.000%

No Known Activations

This feature has no known activations.