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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ebin

-0.90

DragonMagazine

-0.82

earable

-0.79

bnb

-0.76

ratulations

-0.75

 reluct

-0.74

ModLoader

-0.73

ank

-0.72

 warr

-0.72

Mask

-0.72

POSITIVE LOGITS

join

0.75

 Trailer

0.69

joined

0.64

caster

0.63

 Cinem

0.62

capital

0.62

 Garner

0.60

 Paramount

0.60

Kansas

0.59

 Solo

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.