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

uesday

-0.68

ificant

-0.68

 DRAGON

-0.65

 Armageddon

-0.64

 Warp

-0.62

 provisional

-0.62

 Crusade

-0.62

 Decay

-0.61

 Ultra

-0.61

Spec

-0.60

POSITIVE LOGITS

isine

0.87

places

0.72

ðŁĺ

0.70

expr

0.69

 pains

0.69

nam

0.69

Cyr

0.67

 dolls

0.66

yip

0.65

sic

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.