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

Ans

-0.71

 Networks

-0.69

NBN

-0.66

Ara

-0.62

 benches

-0.61

di

-0.59

 isol

-0.59

 involving

-0.58

Nil

-0.58

 Back

-0.58

POSITIVE LOGITS

isSpecialOrderable

0.83

utm

0.79

ä¹ĭ

0.78

mort

0.75

NYSE

0.74

SIGN

0.71

println

0.71

USD

0.69

 guiActiveUnfocused

0.68

aver

0.68

Activations Density 0.000%

No Known Activations

This feature has no known activations.