INDEX

Explanations

specific references to research findings or summaries

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

+#+

-0.49

šet

-0.47

 Мексичка

-0.46

 complejo

-0.46

談社

-0.46

будь

-0.44

 Samaria

-0.43

 ayı

-0.42

 complesso

-0.42

 çöz

-0.42

POSITIVE LOGITS

 promise

0.63

 promised

0.63

WireFormatLite

0.63

)++;

0.61

 nargin

0.58

 surla

0.57

PreExecute

0.57

 hinted

0.56

̍t

0.56

isholm

0.56

Activations Density 0.683%

specific references to research findings or summaries

No Comments

No Known Activations

specific references to research findings or summaries

No Comments

No Known Activations