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

auri

-0.61

â

-0.61

 scorer

-0.60

Liter

-0.60

 sing

-0.59

thread

-0.58

 Community

-0.57

astic

-0.57

 Rational

-0.56

 Metropolitan

-0.56

POSITIVE LOGITS

 neighb

0.81

 destro

0.73

eer

0.69

inia

0.69

 tremend

0.68

orsi

0.68

gress

0.65

 embr

0.65

 Horowitz

0.64

 warr

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.