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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

inges

-0.74

Ack

-0.70

aire

-0.69

ickle

-0.65

inker

-0.62

 streaks

-0.62

ick

-0.60

DU

-0.60

Coh

-0.60

iph

-0.58

POSITIVE LOGITS

 Palest

0.78

çļ

0.76

é¾įåĸļå£«

0.72

ntil

0.71

_-

0.69

ï

0.66

Chel

0.65

Mos

0.65

Orig

0.65

 VIDEOS

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.