INDEX

Explanations

variables and values in a programming or coding context

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

`Double` types in code

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

SharedCtor

-0.46

DataPropertyName

-0.42

 plă

-0.41

cessite

-0.39

autaire

-0.38

elemField

-0.36

tauchen

-0.35

TestFixture

-0.35

çük

-0.35

 placas

-0.35

POSITIVE LOGITS

aarrggbb

0.60

MIDDLEWARE

0.52



0.52

 autorytatywna

0.49

webElementXpaths

0.49

 numberOfRows

0.48

出版年

0.47

MENAFN

0.47

 تضيفلها

0.46

libft

0.45

Activations Density 0.056%

variables and values in a programming or coding context

`Double` types in code

No Comments

No Known Activations