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

resp

-0.70

Veh

-0.69

interrupted

-0.67

usa

-0.67

CTV

-0.64

Ã¯

-0.63

EG

-0.63

GV

-0.62

Ã¨

-0.60

AU

-0.59

POSITIVE LOGITS

anwhile

0.75

gow

0.68

iths

0.67

 whis

0.66

urities

0.65

optional

0.65

isode

0.65

 Twain

0.65

 defic

0.63

pite

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.