INDEX

Explanations

mentions of the word "Park"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 للاسماء

-0.72

 '\\;'

-0.63

esez

-0.61

Byz

-0.60

 >=",

-0.60

 Anglia

-0.56

новниш

-0.55

 Byzantium

-0.55

Hej

-0.55

wifery

-0.55

POSITIVE LOGITS

 Park

4.75

Park

4.44

 park

4.29

 PARK

4.26

park

3.83

PARK

3.72

 parks

3.22

 Parks

2.90

parks

2.76

Parks

2.51

Activations Density 0.054%

mentions of the word "Park"

No Comments

No Known Activations