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

 shove

-0.69

 swipe

-0.67

Rub

-0.63

 rese

-0.60

pmwiki

-0.59

 smack

-0.58

entimes

-0.58

 scratch

-0.58

NRS

-0.58

 jammed

-0.57

POSITIVE LOGITS

ĸļ

0.80

ifer

0.73

aido

0.71

rer

0.69

frames

0.69

agos

0.68

bear

0.68

assic

0.68

efficients

0.66

onel

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.