INDEX

Explanations

elements related to graphical image data and manipulation in programming contexts

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

current index values

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

FormTagHelper

-0.52

 للمعارف

-0.52

XmlAccessType

-0.49

VersionUID

-0.47

 InputDecoration

-0.45

 Majefty

-0.43

exports

-0.43

third

-0.43

WebVitals

-0.42

enablog

-0.42

POSITIVE LOGITS

HasIndex

0.55

 disambiguazione

0.54

 IndexPath

0.47

 index

0.46

 Index

0.45

Hentet

0.44

 AssemblyCulture

0.42

Index

0.42

setof

0.40

tonode

0.40

Activations Density 0.033%

elements related to graphical image data and manipulation in programming contexts

current index values

No Comments

No Known Activations