INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

ebin

-0.74

ymes

-0.74

 Hath

-0.69

ASC

-0.69

Rh

-0.68

upon

-0.66

reon

-0.65

Pg

-0.65

 SHARES

-0.64

 supra

-0.63

POSITIVE LOGITS

 worse

0.81

itaire

0.79

 that

0.78

 THAT

0.71

obyl

0.68

vasive

0.65

that

0.63

ledged

0.62

 mitigation

0.62

ifi

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.