INDEX

Explanations

mentions of hair color and its characteristics, especially gray and white hair

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

hair, grayness, baldness

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

quelize

-0.61

AsUp

-0.57

 Meksiku

-0.56

 فريبيس

-0.54

 Kombat

-0.48

djangoproject

-0.47

IntoConstraints

-0.46

shund

-0.43

elemField

-0.42

󠁢

-0.41

POSITIVE LOGITS

 bald

0.57

age

0.54

 capelli

0.47

 aging

0.47

 Elderly

0.46

 aged

0.46

👵

0.45

Age

0.44

 Aging

0.44

 elderly

0.43

Activations Density 0.008%

mentions of hair color and its characteristics, especially gray and white hair

hair, grayness, baldness

No Comments

No Known Activations