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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

esm

-0.81

ilib

-0.77

é¾įå¥ĳå£«

-0.73

Interstitial

-0.70

EEK

-0.67

Ich

-0.67

interstitial

-0.65

":""},{"

-0.64

ãĥīãĥ©ãĤ´ãĥ³

-0.64

*/(

-0.64

POSITIVE LOGITS

OTUS

0.73

Rug

0.70

ulic

0.64

Cay

0.62

 coincidence

0.61

raq

0.61

rat

0.60

 Halifax

0.59

 accounts

0.57

ya

0.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.