INDEX

Explanations

numeric identifiers within strings

oai_token-act-pair · gpt-3.5-turbo

instances of specific keywords and identifiers

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 Sally

-0.83

Ler

-0.77

Sz

-0.76

 Stew

-0.75

Ens

-0.72

 Elise

-0.71

 Sigma

-0.70

Sak

-0.70

 Isle

-0.69

Ell

-0.69

POSITIVE LOGITS

1.47

bs

1.39

bis

1.29

ber

1.28

bb

1.27

bol

1.26

ba

1.25

bish

1.23

bral

1.20

bi

1.19

Activations Density 0.222%

numeric identifiers within strings

instances of specific keywords and identifiers

No Comments

No Known Activations