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

Eye

-0.68

 damp

-0.63

brace

-0.62

 Courage

-0.62

 Coat

-0.61

Cup

-0.61

 brushes

-0.60

rack

-0.60

 Lerner

-0.59

emate

-0.59

POSITIVE LOGITS

 into

0.95

 INTO

0.93

 onto

0.81

acters

0.73

iseum

0.70

#$#$

0.67

oute

0.66

into

0.66

thumbnails

0.66

 DEBUG

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.