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

pec

-0.64

 Canon

-0.62

sters

-0.59

fig

-0.57

 informant

-0.56

 Eliot

-0.56

 tear

-0.56

 Edit

-0.55

 seals

-0.55

 Robin

-0.55

POSITIVE LOGITS

oaded

0.83

baugh

0.79

ubb

0.74

illard

0.73

borgh

0.72

ailable

0.69

Catalog

0.69

kefeller

0.68

umped

0.68

ernel

0.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.