INDEX

Explanations

quantitative descriptions and dimensions of products

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

Measurements or dimensions with numbers

np_acts-logits-general · gemini-2.0-flash

Huntington disease, Teresa

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

rez

-0.51

 desks

-0.50

mtable

-0.49

-0.48

 desk

-0.47

setCellValue

-0.46

xaml

-0.44

SqlSession

-0.43

struts

-0.42

TintMode

-0.42

POSITIVE LOGITS

 Shakspeare

0.72

 surla

0.65

ILDREN

0.63

 himſelf

0.63

 désolés

0.63

 >=",

0.63

"]="

0.62

 itſelf

0.62

bricht

0.61

 myſelf

0.61

Activations Density 0.087%

quantitative descriptions and dimensions of products

Measurements or dimensions with numbers

Huntington disease, Teresa

No Comments

No Known Activations