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

odon

-0.87

oho

-0.76

 towers

-0.73

ten

-0.73

illion

-0.73

thood

-0.73

cn

-0.70

vard

-0.66

ho

-0.62

fts

-0.61

POSITIVE LOGITS

govtrack

0.84

lication

0.78

aim

0.75

wake

0.72

 circumcision

0.69

contact

0.68

DragonMagazine

0.67

gerald

0.67

ossibility

0.67

 contingency

0.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.