INDEX

Explanations

concepts and terminology related to directed graphs and their properties

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

OrNil

-0.70

ContentAsync

-0.59

cazione

-0.58

MemoryWarning

-0.57

βολ

-0.57

IsContent

-0.57

pushFollow

-0.54

SourceChecksum

-0.54

Referanser

-0.53

 surla

-0.52

POSITIVE LOGITS

 between

0.97

 Between

0.84

 mellan

0.81

 между

0.81

Between

0.79

 BETWEEN

0.79

 zwischen

0.79

between

0.78

 relationship

0.75

 tussen

0.73

Activations Density 2.323%

concepts and terminology related to directed graphs and their properties

No Comments

No Known Activations

concepts and terminology related to directed graphs and their properties

No Comments

No Known Activations