INDEX

Explanations

terms related to distinctions and comparisons between concepts

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

odacty

-0.54

adaptiveStyles

-0.52

郎

-0.50

 pairings

-0.48

ả

-0.48

 onBind

-0.48

 Cavaliers

-0.47

Kết

-0.47

 περιο

-0.47

 Abstraction

-0.46

POSITIVE LOGITS

HtmlAttribute

0.82

Personendaten

0.71

tagHelperRunner

0.70

rawDesc

0.68

rrggbb

0.63

windowFixed

0.62

 utafitiHapana

0.60

EndContext

0.59

);*/

0.59

ResumeLayout

0.58

Activations Density 0.062%

terms related to distinctions and comparisons between concepts

No Comments

No Known Activations