INDEX

Explanations

references to burgers and fried food items

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 الدولى

-0.72

]--;

-0.69

 kasarigan

-0.57

Бахар

-0.57

CodeAttribute

-0.56

 Corne

-0.55

 eventType

-0.55

ägg

-0.54

 lateinit

-0.53

 TType

-0.53

POSITIVE LOGITS

 burger

0.95

 Burger

0.89

 fried

0.84

 burgers

0.83

Burger

0.80

 Burgers

0.75

 Fried

0.75

fried

0.74

fry

0.70

 hamburgers

0.69

Activations Density 0.057%

references to burgers and fried food items

No Comments

No Known Activations