INDEX

Explanations

references to a programming context or environment

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

android context

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

 betweenstory

-0.77

 envisioned

-0.50

 prophe

-0.50

 Biôgrafia

-0.49

 nonUne

-0.49

fortawesome

-0.48

addCriterion

-0.48

 surla

-0.47

uvres

-0.47

的反

-0.47

POSITIVE LOGITS

 AttributeSet

0.59

 Roskov

0.43



0.42

 LayoutInflater

0.41

Lähteet

0.37

GOTREF

0.37

 trajets

0.37

AutoScaleMode

0.37

AttributeSet

0.36

BuildContext

0.36

Activations Density 0.001%

references to a programming context or environment

android context

No Comments

No Known Activations