INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

glomer

-0.93

rosso

-0.84

brids

-0.80

sembly

-0.77

ibles

-0.76

sle

-0.75

ipel

-0.75

kid

-0.74

iak

-0.72

icter

-0.72

POSITIVE LOGITS

 Snapchat

0.77

onal

0.71

ITV

0.70

Xin

0.67

 Bloomberg

0.66

 Lesbian

0.66

 Qualcomm

0.65

 preference

0.64

Ern

0.63

 blackout

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.