INDEX

Explanations

actions related to cooking and food preparation

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

serve, cool, room, cutting, fetching

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

 cook

-0.65

cook

-0.64

 Cook

-0.58

 cooked

-0.57

Cook

-0.55

 cooks

-0.52

 COOK

-0.50

boiling

-0.50

 boiling

-0.49

grill

-0.49

POSITIVE LOGITS

rungsseite

0.53

 betweenstory

0.50

SharedDtor

0.39

Życiorys

0.39

/*:

0.37

 resourceCulture

0.36

ValueStyle

0.35

webElementGuid

0.33

praš

0.33

 actionMode

0.33

Activations Density 0.064%

actions related to cooking and food preparation

serve, cool, room, cutting, fetching

No Comments

No Known Activations