INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

 fodder

-0.74

CTV

-0.70

 homicide

-0.68

vernment

-0.68

 Investig

-0.64

OIL

-0.63

lance

-0.62

hatt

-0.61

 ..........

-0.61

invest

-0.60

POSITIVE LOGITS

nesday

0.71

wcs

0.70

 Rapt

0.67

abe

0.63

ppelin

0.63

acha

0.63

ouston

0.61

66666666

0.60

hett

0.60

rik

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.