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

ieth

-0.75

iol

-0.65

MSG

-0.65

 motions

-0.64

sap

-0.64

Sy

-0.63

iae

-0.63

arma

-0.62

iac

-0.61

 forces

-0.60

POSITIVE LOGITS

Redd

0.75

Leaks

0.75

krit

0.73

anza

0.71

omorph

0.70

merce

0.69

unct

0.68

ãĥ¤

0.68

çīĪ

0.66

ħĭ

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.