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

ÃŁ

-0.75

»

-0.74

 subt

-0.66

oux

-0.65

rams

-0.65

bour

-0.64

 Goodman

-0.63

ida

-0.63

ãĤ¼

-0.62

asher

-0.62

POSITIVE LOGITS

ashtra

0.77

ovember

0.76

 acknow

0.72

civil

0.69

theless

0.69

IRC

0.69

ottest

0.69

 Hobby

0.68

 worsh

0.66

 Normandy

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.