INDEX

Explanations

references to figures and sections within a scientific or medical document

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

section numbers 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

ActionCreators

-0.54

 AssemblyCulture

-0.53

 propOrder

-0.50

AddHtmlAttribute

-0.49

 pinulongan

-0.47

Geplaatst

-0.47

tinyos

-0.46

WriteAttribute

-0.45

IntoConstraints

-0.45

RectangleBorder

-0.45

POSITIVE LOGITS

 hObject

0.43

cshtml

0.41

msgSender

0.38

Diwedd

0.35

uite

0.34

minha

0.34

 LIVES

0.33

 Scheiben

0.33

ambi

0.33

 bağlantılar

0.33

Activations Density 0.012%

references to figures and sections within a scientific or medical document

section numbers and figures

No Comments

No Known Activations