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

essor

-0.70

olithic

-0.68

0000000000000000

-0.68

aned

-0.68

inav

-0.67

uni

-0.66

Tag

-0.65

ealing

-0.65

Pwr

-0.65

cellence

-0.65

POSITIVE LOGITS

glers

0.72

 hereafter

0.66

bars

0.65

EQ

0.65

wat

0.64

ttes

0.64

 pige

0.63

chem

0.61

cour

0.60

 Nights

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.