INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

clus

-0.68

 RELEASE

-0.67

clusive

-0.66

 fung

-0.63

UGE

-0.63

utic

-0.61

metry

-0.59

 Ambro

-0.59

ABE

-0.58

ressing

-0.58

POSITIVE LOGITS

angel

0.82

leon

0.80

osate

0.79

oof

0.74

Spoiler

0.73

itely

0.68

Sources

0.68

walk

0.68

obook

0.66

roots

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.