INDEX

Explanations

terms related to food and its contextual implications, particularly in health and nutrition

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

"Food" followed by certain nouns

np_acts-logits-general · gemini-2.0-flash

food and related contexts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Pfund

-0.62

ractable

-0.55

=$?

-0.51

 hard

-0.50

EDEFAULT

-0.48

 desem

-0.48

pdo

-0.47

 pemimpin

-0.47

ventus

-0.47

 tvrd

-0.47

POSITIVE LOGITS

KommentareTeilen

0.77

stuff

0.73

 препратки

0.68

 nakalista

0.66

stuffs

0.66

 stuffs

0.65

Food

0.61

 food

0.60

Foods

0.60

 FOOD

0.60

Activations Density 0.137%

terms related to food and its contextual implications, particularly in health and nutrition

"Food" followed by certain nouns

food and related contexts

No Comments

No Known Activations