INDEX

Explanations

references to specific metrics or entities in various domains

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

following specific nouns

np_acts-logits-general · gemini-2.0-flash

specific nouns and entities

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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



-0.79

TypedDataSet

-0.76

 للمعارف

-0.72

 Normdatei

-0.66

دانشنامهٔ

-0.66

UrlResolution

-0.64

 esternos

-0.63

RenderAtEndOf

-0.63

AsUp

-0.62

 ffilmiau

-0.62

POSITIVE LOGITS

 propre

0.34

 próprios

0.30

 menge

0.29

̩

0.29

ró

0.28

 Kruse

0.28

 esperaba

0.28

 unfortunately

0.28

ó

0.28

sí

0.27

Activations Density 1.092%

references to specific metrics or entities in various domains

following specific nouns

specific nouns and entities

No Comments

No Known Activations