INDEX

Explanations

sequences of letters and specific coding or technical terms

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

technical entities and scientific materials

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

CWE

-0.47

 fotografico

-0.42

contentLoaded

-0.42

 termica

-0.42

 purpoſe

-0.39

❋

-0.37

 thermique

-0.37

 Unterscheidung

-0.36

 auttaa

-0.36

izante

-0.35

POSITIVE LOGITS

baidu

0.89

jstor

0.72

Jwt

0.63

 الرياضيه

0.56

 ویکی‌پدیای

0.56

WebElementEntity

0.54

VisualStudio

0.52

ibm

0.50

منابع

0.50

 ويكيميديا

0.50

Activations Density 0.000%

sequences of letters and specific coding or technical terms

technical entities and scientific materials

No Comments

No Known Activations