INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

ividual

-0.80

BuyableInstoreAndOnline

-0.74

Ïģ

-0.65

 cryptoc

-0.63

tumblr

-0.61

Books

-0.60

emo

-0.60

ulz

-0.60

Ñı

-0.60

Desktop

-0.60

POSITIVE LOGITS

 Trinity

0.71

 summers

0.66

 opposite

0.63

 Sheridan

0.63

renheit

0.62

 arbitration

0.62

 Peel

0.62

Nun

0.61

reen

0.61

 Rounds

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.