INDEX

Explanations

code-related structure and imports

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

code imports and declarations

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

RenderAtEndOf

-0.57

GOTREF

-0.52

 وتسجيلات

-0.49

 initComponents

-0.47

Hentet

-0.47

VersionUID

-0.47

featureID

-0.46

webElementXpaths

-0.45

Билгалдахарш

-0.44

IContainer

-0.42

POSITIVE LOGITS

 pinulongan

0.52

 chande

0.47

tangentMode

0.40

Kesimpulan

0.40

Terms

0.39

går

0.39

vician

0.39

nå

0.39

UDO

0.39

 sér

0.39

Activations Density 0.011%

code-related structure and imports

code imports and declarations

No Comments

No Known Activations