INDEX

Explanations

terms associated with "feeding" and nutritional input

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 Lott

-0.76

Precalculus

-0.76

psons

-0.76

 Xperia

-0.75

 Μαρ

-0.73

 CommonModule

-0.69

resolvers

-0.68

 contextLoads

-0.68

 Theater

-0.68

 xperia

-0.67

POSITIVE LOGITS

 feed

1.66

 feeds

1.65

 Feed

1.58

feed

1.53

Feed

1.48

 FEED

1.47

feeds

1.46

 Feeds

1.42

FEED

1.40

Feeds

1.30

Activations Density 0.064%

terms associated with "feeding" and nutritional input

No Comments

No Known Activations