INDEX

Explanations

references to explanations or interpretations of scientific models or conditions

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

 surla

-0.57

 ModelExpression

-0.56

EndGlobalSection

-0.56

 يتيمه

-0.53

 onAnimation

-0.51

 بيها

-0.50

 Soal

-0.48

förs

-0.48

Ход

-0.48

动了

-0.48

POSITIVE LOGITS

はじめに

0.58

}$

0.56

 Maladies

0.55

chedelic

0.54

<bos>

0.52

 normal

0.52

 simplifié

0.51

nement

0.50

cipation

0.50

 Traditional

0.50

Activations Density 0.104%

references to explanations or interpretations of scientific models or conditions

No Comments

No Known Activations