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

Negative Logits

ĸļ

-0.89

pse

-0.84

sembly

-0.72

soDeliveryDate

-0.71

 Democr

-0.69

 taxp

-0.69

interstitial

-0.67

 welf

-0.67

 Lilith

-0.66

 constitu

-0.66

POSITIVE LOGITS

mys

0.78

emis

0.71

bugs

0.63

uracy

0.63

vous

0.62

Platform

0.61

err

0.61

du

0.60

whe

0.60

pson

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.