INDEX

Explanations

technical terminology and numerical data associated with various fields

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

foreign language text

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

 ब्रेकडाउन

-0.63

 ſch

-0.61

StoreMessageInfo

-0.59

 Administrativna

-0.57

 ſind

-0.56

 تعدى

-0.54

RenderAtEndOf

-0.54

⤹

-0.54

 Verſ

-0.54

нгред

-0.53

POSITIVE LOGITS

 botas

0.32

関連項目

0.31

kologi

0.30

Hauptartikel

0.30

weil

0.29

พล

0.29

GEBURTS

0.28

 kering

0.28

 Trock

0.28

we

0.28

Activations Density 1.569%

technical terminology and numerical data associated with various fields

foreign language text

No Comments

No Known Activations