INDEX

Explanations

references to characters or elements from video game narratives

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

OGND

-0.57

 становника

-0.56

LookAnd

-0.55

autonomie

-0.54

 média

-0.54

 avoit

-0.53

 avoient

-0.53

urlopen

-0.53

Executives

-0.52

(>

-0.51

POSITIVE LOGITS

 discovers

0.58

 flashbacks

0.57

Numerology

0.57

hassee

0.54

fib

0.52

venge

0.52

 awakens

0.52

cro

0.52

cru

0.51

ggere

0.50

Activations Density 2.056%

references to characters or elements from video game narratives

No Comments

No Known Activations