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

estine

-0.74

ensen

-0.72

numbered

-0.72

rencies

-0.72

é¾įåĸļå£«

-0.70

umbered

-0.69

apsed

-0.68

ittee

-0.68

rawdownloadcloneembedreportprint

-0.67

scroll

-0.67

POSITIVE LOGITS

 Swanson

0.75

 Shepherd

0.73

loo

0.71

 ranc

0.69

 Cooke

0.68

 Laos

0.67

 Howell

0.66

 hello

0.65

 Mong

0.65

 Cruz

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.