INDEX

Explanations

non-verbal cues or indicators of emphasis, often represented by special characters or formatting

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

French words and phrases

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

LookAnd

-0.56

 autorytatywna

-0.54

Panamoan

-0.46

دانشنامهٔ

-0.43

 <=",

-0.42

LEncoder

-0.41

contentLoaded

-0.41

NewGuid

-0.41

GHIJKLM

-0.40

GTCX

-0.40

POSITIVE LOGITS

 soeur

0.52

Amer

0.47

 typique

0.47

 plufieurs

0.47

Clik

0.46

luß

0.44

 secondaire

0.44

 Ketten

0.44

getNum

0.43

 vectorielle

0.43

Activations Density 0.055%

non-verbal cues or indicators of emphasis, often represented by special characters or formatting

French words and phrases

No Comments

No Known Activations