INDEX

Explanations

structured comment syntax used in code documentation

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

constant definitions

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

tagHelperRunner

-0.68

MessageOf

-0.56

IntoConstraints

-0.56

styleType

-0.51

舺

-0.50

oredCriteria

-0.50

 виправивши

-0.50



-0.50

 Biôgrafia

-0.50

lacable

-0.48

POSITIVE LOGITS

GOTREF

0.36

RunWith

0.35

 poveznice

0.34

 Observed

0.34

 ModelExpression

0.34

colgroup

0.33

 Sciences

0.33

 Testing

0.32

ggings

0.31

 копи

0.31

Activations Density 0.001%

structured comment syntax used in code documentation

constant definitions

No Comments

No Known Activations