INDEX

Explanations

mathematical notation, particularly involving equations and formal definitions

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

Mathematical or logical expressions

np_acts-logits-general · gemini-2.0-flash

then or that

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

脚注の使い方

-0.64

BeginInit

-0.59

SBATCH

-0.59

bef

-0.59

 itſelf

-0.58

Handlung

-0.57

Jef

-0.57

raft

-0.56

 pantal

-0.54

Xy

-0.54

POSITIVE LOGITS

queryInterface

0.57

før

0.54

PostInfinity

0.53

Sucesor

0.52

 yalnız

0.50

 carrés

0.49

 pregunto

0.48

 funcionales

0.48

 faune

0.47

جوايز

0.46

Activations Density 1.276%

mathematical notation, particularly involving equations and formal definitions

Mathematical or logical expressions

then or that

No Known Activations