INDEX

Explanations

elements related to figures, tables, and mathematical expressions

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

cross-references to figures and tables

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

 propOrder

-0.51

دانشنامهٔ

-0.50

 poveznice

-0.48

angliski

-0.46

Spoljašnje

-0.45

󠁣

-0.45

IVEREF

-0.44

CodedInputStream

-0.43

 académico

-0.42

stylers

-0.42

POSITIVE LOGITS

GTCX

0.44

FXMLLoader

0.42

AnimationsModule

0.42

ImageContext

0.40

rawDesc

0.40

Dtor

0.38

ThemeProvider

0.37

}")]

0.36

dil

0.36

')}}">

0.36

Activations Density 0.034%

elements related to figures, tables, and mathematical expressions

cross-references to figures and tables

No Comments

No Known Activations