INDEX

Explanations

repeated occurrences of the word "the."

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

than, compared to, opposed to, unlike

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

 polig

-0.43

liferay

-0.40

 arşivlendi

-0.39

AppMethodBeat

-0.38

 PeEnEo

-0.37

 ciel

-0.36

toMatchSnapshot

-0.36

 téléchargez

-0.35

 appelez

-0.35

executeUpdate

-0.35

POSITIVE LOGITS

 usual

0.64

########.

0.62

 previous

0.62

 heretofore

0.56

 current

0.54

 diğer

0.54

 former

0.53

 atuais

0.53

 sebelumnya

0.53

 earlier

0.52

Activations Density 0.086%

repeated occurrences of the word "the."

than, compared to, opposed to, unlike

No Comments

No Known Activations