INDEX

Explanations

references to user groups and organization structures

oai_token-act-pair · gpt-4o-mini Triggered by @bot

group and groups

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 հղումներ

-0.63

 onPostExecute

-0.58

AndEndTag

-0.58

 فريبيس

-0.56

rungsseite

-0.54

دانشنامهٔ

-0.53

存于互联网档案馆

-0.52

PYX

-0.52

 ioutil

-0.50

 intStringLen

-0.50

POSITIVE LOGITS

 group

0.89

 groups

0.86

 groupe

0.73

 Group

0.73

 groupes

0.71

Group

0.71

group

0.69

 Groups

0.69

 GROUP

0.69

Groups

0.68

Activations Density 0.034%

references to user groups and organization structures

group and groups

No Comments

No Known Activations