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

inosaur

-0.74

pmwiki

-0.71

 CONTR

-0.69

EMOTE

-0.69

thood

-0.65

 Profession

-0.65

 Contract

-0.62

{\

-0.62

 Duff

-0.62

odder

-0.61

POSITIVE LOGITS

gallery

0.78

worms

0.78

uli

0.75

atography

0.73

kell

0.72

urer

0.70

worm

0.70

wcs

0.69

ivia

0.68

come

0.68

Activations Density 0.000%

No Known Activations

This feature has no known activations.