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

 Antar

-1.02

 Adin

-0.93

iru

-0.78

 consum

-0.74

 Canaver

-0.71

 Chandra

-0.69

ascus

-0.68

 exha

-0.68

romeda

-0.68

urion

-0.68

POSITIVE LOGITS

iquette

1.01

cens

0.75

DEN

0.71

Gate

0.71

clinton

0.69

Released

0.69

ois

0.68

priv

0.68

prison

0.66

RH

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.