INDEX

Explanations

actions related to eating and related food consumption

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 arqu

-0.71

']))

-0.70

ρίου

-0.70

hii

-0.69

ں

-0.67

}}],

-0.66

illian

-0.64

mij

-0.63

 Prou

-0.63

 Nilsson

-0.62

POSITIVE LOGITS

eat

2.94

 eats

2.60

 eating

2.60

Eat

2.57

 eaten

2.45

Eat

2.42

EAT

2.39

 Eating

2.37

Eating

2.36

ate

2.29

Activations Density 0.052%

actions related to eating and related food consumption

No Comments

No Known Activations