INDEX

Explanations

terms and metrics related to body mass and obesity measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

:✨

-0.77

consulté

-0.59

pions

-0.52

mix

-0.50

 named

-0.49

Mix

-0.48

ear

-0.47

hoot

-0.46

 terse

-0.46

dienst

-0.45

POSITIVE LOGITS

 obesity

1.12

 obese

1.07

 Obesity

1.05

 overweight

1.04

BMI

1.00

Obesity

0.98

 weight

0.97

fat

0.94

 Weight

0.88

WEIGHT

0.87

Activations Density 0.339%

terms and metrics related to body mass and obesity measurements

No Comments

No Known Activations