INDEX

Explanations

references to food and dining experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 faſt

-0.67

Eſ

-0.59

styleType

-0.55

 againſt

-0.55

ownik

-0.54

Contactez

-0.53

 opér

-0.52

 Anſ

-0.52

 Contactez

-0.51

 quæ

-0.51

POSITIVE LOGITS

 tasted

0.73

 presentation

0.60

 correctes

0.59

 moist

0.56

 portions

0.53

 Presentation

0.52

 smelled

0.52

 Portions

0.51

Presentation

0.51

 hubby

0.51

Activations Density 0.081%

references to food and dining experiences

No Comments

No Known Activations