INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 Flavoring

-1.15

Downloadha

-0.95

olkien

-0.84

anish

-0.78

Sov

-0.75

 Marketable

-0.74

 seiz

-0.73

ilage

-0.72

cit

-0.72

irit

-0.72

POSITIVE LOGITS

XY

0.64

vote

0.62

©¶æ

0.62

forest

0.61

ðŁĳ

0.60

NG

0.60

 rubble

0.59

 drone

0.59

team

0.58

 Podesta

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.