INDEX

Explanations

locations and settings within the narrative

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

LookAnd

-0.68

\|_{

-0.67

onTap

-0.63

 useCallback

-0.59

ècie

-0.59

 Wissenschaften

-0.58

رشف

-0.58

ServletRequest

-0.58

 sembl

-0.57

 faiths

-0.57

POSITIVE LOGITS

 facilities

0.95

 office

0.85

 hall

0.83

 station

0.82

inghouse

0.81

 house

0.77

 halls

0.77

 room

0.76

 facility

0.75

facilities

0.73

Activations Density 2.793%

locations and settings within the narrative

No Comments

No Known Activations