INDEX

Explanations

questions or phrases expressing curiosity or inquiry

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

Why questions

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

/**

-0.64

/*

-0.60

twimg

-0.60

 endregion

-0.60

༺

-0.59

JspWriter

-0.58

цезда

-0.57

omiast

-0.56

parsedMessage

-0.54

//

-0.53

POSITIVE LOGITS

Why

1.33

Why

1.31

why

1.05

why

0.98

 Warum

0.94

WHY

0.94

WHY

0.91

 Pourquoi

0.90

 Waarom

0.90

Pourquoi

0.85

Activations Density 0.010%

questions or phrases expressing curiosity or inquiry

Why questions

No Known Activations