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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

oos

-0.74

amina

-0.66

ampton

-0.65

ucks

-0.64

rament

-0.63

umin

-0.63

camp

-0.63

unning

-0.63

uch

-0.62

ventory

-0.61

POSITIVE LOGITS

WARE

0.78

gee

0.73

 largeDownload

0.73

¬¼

0.72

é¾į

0.72

ilus

0.71

âĵĺ

0.71

UTE

0.70

ãĥ¯ãĥ³

0.70

iframe

0.70

Activations Density 0.000%

No Known Activations

This feature has no known activations.