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

vation

-0.80

onds

-0.72

duc

-0.71

iak

-0.68

sbm

-0.67

idences

-0.66

hern

-0.66

ulsion

-0.65

 Quote

-0.65

PLIED

-0.65

POSITIVE LOGITS

 shorth

0.73

ijk

0.72

 consequential

0.72

Ug

0.63

 bulls

0.58

 fencing

0.58

don

0.57

 calves

0.57

 Elastic

0.56

 unsub

0.56

Activations Density 0.000%

No Known Activations

This feature has no known activations.