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

bourg

-0.77

ciating

-0.71

IPM

-0.68

tein

-0.66

Fax

-0.64

fax

-0.63

bia

-0.61

Ó

-0.59

 convol

-0.58

Ask

-0.58

POSITIVE LOGITS

hod

0.69

SEA

0.68

elist

0.66

ettings

0.64

HL

0.63

ritz

0.60

lyak

0.60

vernment

0.59

zbollah

0.59

andals

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.