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

 sqor

-0.73

elsen

-0.73

 Kear

-0.72

quickShipAvailable

-0.68

RAW

-0.66

§

-0.66

 Chaff

-0.63

ricks

-0.63

REG

-0.62

STE

-0.62

POSITIVE LOGITS

enium

0.85

worms

0.83

icans

0.79

unker

0.73

aned

0.73

worm

0.69

aque

0.66

renheit

0.66

inav

0.65

isters

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.