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

ãĥ¢

-0.63

Stan

-0.62

ãĤ®

-0.60

 replacements

-0.59

 MacArthur

-0.59

 Feinstein

-0.58

ãĥ´

-0.57

ipher

-0.56

EStreamFrame

-0.55

 McCorm

-0.55

POSITIVE LOGITS

reprene

0.86

mund

0.74

mob

0.74

umar

0.72

kh

0.72

este

0.71

xit

0.69

vis

0.68

ecause

0.68

ighth

0.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.