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

Not in Any Lists

No Comments

Negative Logits

FTWARE

-0.79

iversary

-0.78

(@

-0.74

ECK

-0.73

itia

-0.73

ashtra

-0.71

ãĥ¼ãĥĨãĤ£

-0.71

vironment

-0.70

gow

-0.68

BTC

-0.66

POSITIVE LOGITS

paren

0.73

SPONSORED

0.72

atever

0.68

agara

0.68

 Communism

0.67

uer

0.65

 mascul

0.61

olver

0.61

itty

0.61

asions

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.