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

 tradem

-0.77

strate

-0.69

 commissions

-0.69

mares

-0.66

 commission

-0.63

emporary

-0.63

 surve

-0.62

ADE

-0.62

fare

-0.61

unta

-0.61

POSITIVE LOGITS

Reviewer

0.99

æ©

0.91

govtrack

0.82

Vo

0.78

SPONSORED

0.77

ãĥ³ãĤ¸

0.75

Äĩ

0.73

save

0.73

ãĤª

0.72

ãĥ´ãĤ¡

0.71

Activations Density 0.000%

No Known Activations

This feature has no known activations.