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

agements

-0.77

 Lethal

-0.75

 Promotion

-0.74

goers

-0.70

 Mayhem

-0.68

zbollah

-0.66

 Tanz

-0.64

 Rampage

-0.64

 Proxy

-0.64

urable

-0.63

POSITIVE LOGITS

elsen

0.80

wl

0.75

dating

0.73

hair

0.73

dust

0.71

ãĤ§

0.71

court

0.70

fing

0.67

fur

0.65

roo

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.