INDEX

Explanations

elements related to programming or code implementation structures

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

user input in code contexts

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

saraba

-0.51

mayer

-0.47

ScopeManager

-0.45

 sponsored

-0.44

NameInMap

-0.43

альное

-0.42

ThroughAttribute

-0.42

citroën

-0.42

yarnpkg

-0.42

 sliced

-0.42

POSITIVE LOGITS

Personensuche

0.47

RetentionPolicy

0.45

 EconPapers

0.44

XmlRootElement

0.40

 désolés

0.40

SharedCtor

0.38

 Photocase

0.37

Segue

0.36

 FetchType

0.35

InitStruct

0.35

Activations Density 0.006%

elements related to programming or code implementation structures

user input in code contexts

No Comments

No Known Activations