INDEX

Explanations

phrases associated with health risks and medical contexts

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

Weight loss, dieting, or interventions

np_acts-logits-general · gemini-2.0-flash

weight loss and diet choices

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

ViewFeatures

-0.59

 виправивши

-0.56

 pinball

-0.54

Personendaten

-0.54

DoubleQuotes

-0.54

 Савезне

-0.53

########.

-0.53

 chó

-0.51

spaceBetween

-0.50

oco

-0.50

POSITIVE LOGITS

 weight

1.54

 Weight

1.44

 dieting

1.34

Weight

1.32

 diet

1.31

 WEIGHT

1.29

weight

1.25

 slimming

1.15

WEIGHT

1.12

diet

1.11

Activations Density 0.213%

phrases associated with health risks and medical contexts

Weight loss, dieting, or interventions

weight loss and diet choices

No Known Activations