INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

MSI

-0.75

 Jaguar

-0.71

 Signature

-0.71

 Hundred

-0.69

 Secondly

-0.68

RSA

-0.68

 Kraken

-0.67

 Cull

-0.67

 GROUP

-0.67

 GENERAL

-0.66

POSITIVE LOGITS

Reviewed

0.87

tein

0.82

testers

0.81

thia

0.72

abl

0.70

ometry

0.68

rating

0.68

yden

0.67

 foll

0.66

choice

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.