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

ains

-0.91

å§

-0.84

forts

-0.83

nces

-0.81

edom

-0.79

 stops

-0.72

ements

-0.72

ablishment

-0.71

cheon

-0.70

rats

-0.70

POSITIVE LOGITS

ixel

0.68

 Balloon

0.66

HC

0.66

TBA

0.65

uu

0.64

 Adren

0.63

ould

0.62

tera

0.61

Ther

0.61

Thread

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.