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

 Antar

-0.75

 nond

-0.70

geries

-0.65

 heter

-0.64

 Cowboys

-0.60

 prevention

-0.60

AES

-0.59

 sorely

-0.59

 anonymity

-0.58

 Assassins

-0.58

POSITIVE LOGITS

sted

0.76

conom

0.75

eele

0.73

aire

0.72

ove

0.69

Streamer

0.69

omi

0.69

Hunt

0.68

enment

0.68

sea

0.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.