INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

ilial

-0.76

raph

-0.74

isson

-0.73

untled

-0.73

atown

-0.71

acus

-0.71

 grips

-0.71

akov

-0.71

astered

-0.70

chell

-0.69

POSITIVE LOGITS

é¾įå

0.70

aroo

0.69

Num

0.69

 Thing

0.68

 Voter

0.68

 Idea

0.68

 Week

0.66

Nom

0.64

makers

0.64

 Foss

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.