INDEX

Explanations

references to food and catering services

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

food, snacks, and refreshments

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

 pinulongan

-0.66

 régle

-0.61

 disambiguazione

-0.59

 collè

-0.55

 femininas

-0.55

 yüzde

-0.53

 préc

-0.52

 panoramique

-0.52

 femininos

-0.52

 pozy

-0.52

POSITIVE LOGITS

 refreshments

1.52

 refreshment

1.09

 snacks

0.81

 Snacks

0.81

 snack

0.65

Snacks

0.63

 Snack

0.61

 supplies

0.57

 Refresh

0.56

food

0.55

Activations Density 0.001%

references to food and catering services

food, snacks, and refreshments

No Comments

No Known Activations