INDEX

Explanations

comments in code

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

This function/general initialization

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

تفصیلات

-0.41

 >=",

-0.38

탤

-0.38

出版年

-0.36

 schild

-0.35

Hozzáférés

-0.33

URIComponent

-0.33

 تضيفلها

-0.33

SceneManagement

-0.33

もしか

-0.32

POSITIVE LOGITS

tagHelperRunner

0.56

CloseOperation

0.49

śla

0.48

alaya

0.46

 mußte

0.46

uș

0.46

 kennt

0.44

ooth

0.44

allon

0.44

いしい

0.44

Activations Density 0.010%

comments in code

This function/general initialization

No Comments

No Known Activations