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

iani

-0.72

interstitial

-0.69

modules

-0.68

UGE

-0.68

eki

-0.65

 inaug

-0.62

 Muse

-0.62

 Dise

-0.62

abi

-0.61

 imaginable

-0.61

POSITIVE LOGITS

irlf

0.75

racuse

0.70

ertodd

0.70

amac

0.63

ioned

0.62

oras

0.62

xus

0.62

 dors

0.61

pedia

0.61

bits

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.