INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

lus

-0.72

 distingu

-0.72

 Malf

-0.70

fil

-0.69

 gobl

-0.68

 happ

-0.68

dra

-0.67

 burg

-0.65

é£

-0.65

 aggregation

-0.64

POSITIVE LOGITS

SIGN

0.81

enance

0.78

 Michaels

0.75

akeru

0.73

papers

0.72

ETS

0.72

unity

0.67

SourceFile

0.66

 Mata

0.66

Â¯

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.