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

regor

-0.76

 suscept

-0.72

 advoc

-0.69

aukee

-0.68

 Wonders

-0.67

 helicop

-0.67

hedon

-0.66

apter

-0.65

 religions

-0.65

bos

-0.65

POSITIVE LOGITS

PI

0.73

 Shutdown

0.67

viks

0.65

KA

0.65

Elm

0.64

bourg

0.63

amba

0.63

PN

0.62

Reviewed

0.62

NEY

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.