INDEX

Explanations

references to figures and graphical elements in text

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

includegraphics and figures

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

tvguidetime

-0.40

rungsseite

-0.40

intios

-0.40

">—

-0.39

Clik

-0.38

 السر

-0.35

webElementXpaths

-0.35

enumii

-0.35

Nm

-0.35

eleste

-0.35

POSITIVE LOGITS

graphicx

0.84

Bronnen

0.57

AnimationsModule

0.54

graphic

0.54

ographic

0.52

 graphics

0.51

IGraphics

0.50

 graphic

0.49

ocyto

0.48

includegraphics

0.46

Activations Density 0.000%

references to figures and graphical elements in text

includegraphics and figures

No Comments

No Known Activations