INDEX

Explanations

mentions of California and related institutions or contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 OGSÅ

-0.65

BoxShadow

-0.61

 blick

-0.60

webElementXpaths

-0.58

Mink

-0.57

able

-0.56

ctr

-0.55

 הופ

-0.54

CPtr

-0.54

 Urugu

-0.53

POSITIVE LOGITS

 California

2.12

California

1.96

 CALIFORNIA

1.79

 Calif

1.71

 california

1.70

 Califor

1.67

CALIFORNIA

1.66

 Californian

1.64

california

1.56

Calif

1.53

Activations Density 0.040%

mentions of California and related institutions or contexts

No Comments

No Known Activations