INDEX

Explanations

questions and inquiries related to understanding or assessing situations

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

question words

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

WebElementEntity

-0.56

InputBorder

-0.46

ỡng

-0.45

createNewFile

-0.45

 Voiture

-0.43

 PopupWindow

-0.41

adaptiveStyles

-0.41

<!--

-0.41

 BoxDecoration

-0.40

 itemprop

-0.40

POSITIVE LOGITS

 Waray

0.51

 øns

0.46

 egne

0.46

uves

0.45

Maybe

0.45

 możli

0.45

stdc

0.44

 τί

0.43

 limitée

0.43

 dikk

0.43

Activations Density 0.021%

questions and inquiries related to understanding or assessing situations

question words

No Comments

No Known Activations