INDEX

Explanations

words and punctuation used in scientific procedures

oai_token-act-pair · gemini-2.0-flash

New Auto-Interp

Configuration

chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.24.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.24.hook_resid_post

Architecture

jumprelu

Context Size

1,024

Dataset

chanind/pile-uncopyrighted-gemma-1024-abbrv-1B

Embeds

IFrame

Link

Negative Logits

 Otros

-0.51

ほうが

-0.47

 União

-0.45

 assay

-0.45

 päät

-0.45

biór

-0.44

 lavorato

-0.43

 Bucure

-0.43

notNull

-0.43

(*

-0.43

POSITIVE LOGITS

 дописавши

0.71

 commercially

0.69

principalColumn

0.63

[@"

0.63

 GenerationType

0.62

 >=",

0.60

 estekak

0.59

ViewById

0.57

文献

0.56

 publicly

0.56

Activations Density 1.047%

words and punctuation used in scientific procedures

No Known Activations