INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

Ì¶

-0.87

vantage

-0.78

icter

-0.76

ESH

-0.70

advertising

-0.68

 belie

-0.66

%]

-0.66

irtual

-0.65

erning

-0.65

uminati

-0.64

POSITIVE LOGITS

fman

0.72

cknow

0.69

strings

0.67

 Standing

0.66

 exerc

0.66

 Claud

0.66

Tok

0.65

Tok

0.63

 Proced

0.62

ault

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.