INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

OTOS

-0.61

 cracks

-0.59

enthal

-0.59

 spaces

-0.58

Marginal

-0.57

 vetoed

-0.57

itational

-0.56

 voiced

-0.56

 fumes

-0.56

iting

-0.55

POSITIVE LOGITS

¶ħ

0.83

byter

0.82

aternity

0.74

xit

0.73

upuncture

0.73

atl

0.72

etheless

0.71

ocrat

0.71

ath

0.70

sych

0.69

Activations Density 0.000%

No Known Activations

This feature has no known activations.