INDEX

Explanations

references to specific events or people related to legal and criminal activities

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

references to identities and their significance in the context of events or situations

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Shutterstock

-0.77

itia

-0.72

vertisement

-0.69

tackle

-0.68

gyn

-0.67

erb

-0.66

arming

-0.66

book

-0.66

vice

-0.65

Bey

-0.65

POSITIVE LOGITS

 identities

1.52

 whereabouts

1.51

 identity

1.46

 extent

1.40

 origins

1.37

 origin

1.30

 precise

1.26

 exact

1.26

 true

1.22

 motives

1.20

Activations Density 0.272%

references to specific events or people related to legal and criminal activities

references to identities and their significance in the context of events or situations

No Comments

No Known Activations