INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

Tud

-0.79

 McDonnell

-0.73

 privile

-0.72

 Vald

-0.65

itsch

-0.65

Tec

-0.63

 Colombia

-0.62

 Cyprus

-0.62

 Drac

-0.62

 plantations

-0.61

POSITIVE LOGITS

omorphic

0.84

PsyNetMessage

0.81

advertising

0.77

ANS

0.76

iots

0.72

ionic

0.71

icone

0.70

inately

0.70

stellar

0.69

mph

0.68

Activations Density 0.000%

No Known Activations

This feature has no known activations.