INDEX

Explanations

references to data structures and user-related information

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

dates and times

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

Personensuche

-0.61

 cherchés

-0.57

 HasFactory

-0.57

rungsseite

-0.56

 defaultstate

-0.54

migrationBuilder

-0.50

각주

-0.47

queryInterface

-0.47

Дереккөздер

-0.46

moveToFirst

-0.45

POSITIVE LOGITS

webElementXpaths

0.42

ORPG

0.40

bourhood

0.38

 Sense

0.36

 message

0.36

HomeAsUpEnabled

0.35

 sense

0.35

 perime

0.35

 Fors

0.34

 بلو

0.34

Activations Density 0.039%

references to data structures and user-related information

dates and times

No Comments

No Known Activations