INDEX

Explanations

mentions of author or attribution comments

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

Annotation-related code documentation

np_acts-logits-general · gemini-2.0-flash

@author, @return, @param, @see

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

 ModelExpression

-0.68

MLLoader

-0.63

WriteBarrier

-0.62

parsedMessage

-0.61

Personendaten

-0.60

GenerationType

-0.59

 AssemblyCulture

-0.59

Obrázky

-0.58

enterOuterAlt

-0.58

 simplifié

-0.57

POSITIVE LOGITS

author

0.66

see

0.63

return

0.53

Title

0.52

since

0.52

noinspection

0.51

uml

0.48

baño

0.47

category

0.47

version

0.45

Activations Density 0.082%

mentions of author or attribution comments

Annotation-related code documentation

@author, @return, @param, @see

No Comments

No Known Activations