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

orno

-0.74

elsen

-0.72

artney

-0.71

istries

-0.71

ousand

-0.69

irez

-0.65

 cleanup

-0.64

 volunteer

-0.64

 amnesty

-0.63

asions

-0.61

POSITIVE LOGITS

scar

0.79

-+-+

0.73

bid

0.69

Sph

0.68

morrow

0.66

scrib

0.65

 Oswald

0.65

vest

0.65

 condem

0.65

 Fraz

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.