INDEX

Explanations

terms related to espionage and spying

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

terms related to espionage and intelligence activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 12-res-jb

Configuration

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

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_post

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

esville

-0.75

este

-0.64

xual

-0.64

 Mint

-0.60

 Lancet

-0.59

 Tomb

-0.58

Vox

-0.58

 Centauri

-0.56

 dysph

-0.56

Kot

-0.56

POSITIVE LOGITS

ware

1.16

glass

1.05

plane

0.95

 satellites

0.88

sonian

0.87

agency

0.86

planes

0.84

rolet

0.81

craft

0.81

ritz

0.79

Activations Density 0.106%

terms related to espionage and spying

terms related to espionage and intelligence activities

No Comments

No Known Activations