INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

atl

-0.81

gom

-0.79

llah

-0.78

hart

-0.77

paralle

-0.75

JSON

-0.71

 Strongh

-0.71

merce

-0.71

humans

-0.69

heim

-0.69

POSITIVE LOGITS

 report

0.92

 Whit

0.68

report

0.65

 caps

0.63

MAC

0.63

 Russ

0.62

 Wales

0.61

ueller

0.60

Mer

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.