INDEX

Explanations

documentation-related terms and structures

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

javadoc and documentation comments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.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

principalColumn

-0.49

IActionResult

-0.47

 Lokales

-0.45

transQ

-0.44

fromnode

-0.41

förderung

-0.41

errHandler

-0.40

itinéraire

-0.40

 astore

-0.39

 intptr

-0.39

POSITIVE LOGITS

avadoc

0.82

 documentation

0.81

doc

0.75

 Documentation

0.71

 documenta

0.68

 documenting

0.66

 docs

0.66

 comments

0.65

Documentation

0.63

Doc

0.63

Activations Density 0.046%

documentation-related terms and structures

javadoc and documentation comments

No Comments

No Known Activations