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

 endorsements

-0.65

 voices

-0.64

Osw

-0.64

sie

-0.61

ipers

-0.60

interstitial

-0.60

ressing

-0.59

 cough

-0.58

ãħĭ

-0.58

 Scha

-0.58

POSITIVE LOGITS

externalActionCode

0.82

ashtra

0.77

anical

0.76

aur

0.74

assian

0.72

ounty

0.71

Catalog

0.70

ogo

0.68

riad

0.68

 bounty

0.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.