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

vati

-0.90

washer

-0.74

cho

-0.71

EStreamFrame

-0.70

 Aval

-0.68

DIT

-0.68

zona

-0.66

amo

-0.65

oslav

-0.63

terness

-0.63

POSITIVE LOGITS

Times

0.77

ega

0.72

 lawy

0.68

 brainstorm

0.62

enty

0.59

 Times

0.59

 counsel

0.58

Truth

0.58

ourcing

0.57

 trusts

0.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.