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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

cher

-0.73

 laughter

-0.71

DEN

-0.69

VIDIA

-0.68

chery

-0.66

anton

-0.65

chers

-0.65

kowski

-0.63

 Papers

-0.62

iety

-0.61

POSITIVE LOGITS

¥µ

0.69

OVA

0.63

ĪĴ

0.62

 loophole

0.61

aged

0.60

 flip

0.60

regor

0.60

ŃĶ

0.58

ħĭ

0.57

vironments

0.56

Activations Density 0.000%

No Known Activations

This feature has no known activations.