INDEX

Explanations

references to programming concepts and properties related to APIs and session management

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

Followed by certain words or numbers

np_acts-logits-general · gemini-2.0-flash

version numbers and identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 himself

-1.34

 Himself

-1.01

himself

-0.99

 koji

-0.86

 који

-0.81

 său

-0.79

 должен

-0.76

 elettrico

-0.74

 nostru

-0.69

 був

-0.68

POSITIVE LOGITS

 herself

0.95

 αυτή

0.58

 polska

0.55

she

0.51

 internetowa

0.50

 koja

0.49

herself

0.48

 zwią

0.48

 која

0.46

 такая

0.46

Activations Density 0.109%

references to programming concepts and properties related to APIs and session management

Followed by certain words or numbers

version numbers and identifiers

No Comments

No Known Activations