INDEX

Explanations

references to software licensing and usage terms

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

`//` comments

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

ésultats

-0.80

EndGlobalSection

-0.79

featureID

-0.77

 FetchType

-0.77

 erſt

-0.75

 JpaRepository

-0.74

 sumpay

-0.74

 queſta

-0.74

 kaarangay

-0.74

 Italijani

-0.73

POSITIVE LOGITS

↵

0.32

static

0.29

();

0.29

]';

0.29

Version

0.29

《

0.28

Un

0.28

';

0.27

Activations Density 0.010%

references to software licensing and usage terms

`//` comments

No Comments

No Known Activations