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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Ã©e

-0.72

terday

-0.66

'?

-0.66

 Annotations

-0.66

reys

-0.65

 Twins

-0.63

dden

-0.63

interstitial

-0.62

?'"

-0.60

Ã©s

-0.60

POSITIVE LOGITS

itiz

0.75

pler

0.73

natureconservancy

0.70

audio

0.63

hent

0.60

leans

0.59

ugen

0.59

wave

0.58

license

0.58

afi

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.