INDEX

Explanations

expressions of reasons and explanations

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

"why" after questions

np_acts-logits-general · gemini-2.0-flash

asking why

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

IsPostBack

-0.53

 لينك

-0.50

richTextPanel

-0.46

CppMethod

-0.44

ảnh

-0.43

 Infórmanos

-0.43

mona

-0.43

Hauptartikel

-0.42

 متعلقه

-0.41

rawtypes

-0.41

POSITIVE LOGITS

why

4.13

why

3.40

Why

3.11

Why

3.07

 pourquoi

2.83

WHY

2.75

WHY

2.73

 reason

2.68

 reasons

2.63

 waarom

2.62

Activations Density 0.554%

expressions of reasons and explanations

"why" after questions

asking why

No Comments

No Known Activations