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

IPM

-0.71

 Nose

-0.65

Moj

-0.64

 Postal

-0.63

-0.62

Â§

-0.61

 Anonymous

-0.61

Peg

-0.58

 polyg

-0.58

Sic

-0.58

POSITIVE LOGITS

rely

0.75

rats

0.75

cks

0.67

psey

0.66

ally

0.66

Carter

0.64

agree

0.64

 Bale

0.64

urry

0.63

otes

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.