INDEX

Explanations

references to integrated circuits and related technologies

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

"integrated" followed by a specific word

np_acts-logits-general · gemini-2.0-flash

integrated into things

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

Personensuche

-0.68

Ĝ

-0.55

 imageNamed

-0.54

WindowConstants

-0.54

ług

-0.53

SharedCtor

-0.53

 EventEmitter

-0.53

 cyanide

-0.52

́ng

-0.48

 canadensis

-0.47

POSITIVE LOGITS

 into

0.99

Into

0.90

 Into

0.88

 INTO

0.83

 saites

0.76

 seamlessly

0.76

into

0.75

Espèce

0.72

INTO

0.70

Portail

0.69

Activations Density 0.098%

references to integrated circuits and related technologies

"integrated" followed by a specific word

integrated into things

No Comments

No Known Activations