INDEX

Explanations

specific names or proper nouns that represent individuals or entities

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

proper nouns and abbreviations

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

NameInMap

-0.78

Filmografie

-0.62

 الرياضيه

-0.59

SerializedSize

-0.58

Hentet

-0.57

oredCriteria

-0.57

 protoimpl

-0.57

ကိုးကား

-0.57

 defaultstate

-0.56

EndGlobalSection

-0.56

POSITIVE LOGITS

Apparently

0.37

findpost

0.36

 apparently

0.35

 menghar

0.35

LEGGI

0.35

GLOBALS

0.34

 auguri

0.32

 pihak

0.32

 expects

0.31

dengar

0.31

Activations Density 0.015%

specific names or proper nouns that represent individuals or entities

proper nouns and abbreviations

No Comments

No Known Activations