INDEX

Explanations

passive voice and crime or legal terms.

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

évaluateur

-0.73

期刊论文

-0.71

rrggbb

-0.70

CDCl

-0.62

OGND

-0.62

السكان

-0.62

__*/

-0.61

écial

-0.60

ItemBackground

-0.59

 rhestr

-0.58

POSITIVE LOGITS

 arrested

0.69

 found

0.56

 pregi

0.54

found

0.53

 Found

0.52

 charged

0.52

 Charged

0.51

 Arrested

0.51

ar

0.48

 remanded

0.48

Activations Density 0.402%

passive voice and crime or legal terms.

No Known Activations