INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 Sweeney

-0.69

 Anonymous

-0.69

 indent

-0.69

 GOODMAN

-0.69

 UNIVERS

-0.68

 christ

-0.63

 distilled

-0.62

 Publishers

-0.62

 foss

-0.61

 Integ

-0.61

POSITIVE LOGITS

ĸļ

0.84

wered

0.75

é¾įå¥ĳå£«

0.74

omon

0.73

oglobin

0.72

ngth

0.70

andro

0.70

ELD

0.68

okane

0.67

oyal

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.