INDEX

Explanations

terms related to groups of people or crowds

oai_token-act-pair · gpt-4o-mini

New Auto-Interp

Configuration

chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Architecture

jumprelu

Context Size

1,024

Dataset

chanind/pile-uncopyrighted-gemma-1024-abbrv-1B

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Mercier

-0.91

 Patel

-0.80

Portail

-0.79

 tableName

-0.78

 Lipa

-0.76

 Pierson

-0.76

 Ennis

-0.75

forName

-0.75

 Schl

-0.75

 Amis

-0.74

POSITIVE LOGITS

 Crow

1.48

Crow

1.34

 CROW

1.34

 crowds

1.26

crow

1.23

 Crowd

1.23

crowd

1.22

 crow

1.20

Crowd

1.16

 crows

1.13

Activations Density 0.011%

terms related to groups of people or crowds

No Comments

No Known Activations

terms related to groups of people or crowds

No Comments

No Known Activations