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

-0.69

ãĥ¡

-0.62

 hearts

-0.62

ãĥŁ

-0.60

ãĥīãĥ©

-0.59

ãĥĦ

-0.59

ãĤ»

-0.58

blog

-0.57

cdn

-0.56

 landmark

-0.56

POSITIVE LOGITS

 Cobb

0.95

anooga

0.74

 Keller

0.73

ternity

0.72

 Meyer

0.72

ables

0.71

cia

0.71

 Crawford

0.70

 Wick

0.69

 Yose

0.69

Activations Density 0.000%

No Known Activations

This feature has no known activations.