INDEX

Explanations

terms related to holes or openings in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

Portail

-0.88

aarrggbb

-0.81

WebElementEntity

-0.75

liesslich

-0.74

קישורים

-0.70

pagni

-0.69

AsUp

-0.68

Rujuakan

-0.66

">//

-0.66

GraphicsUnit

-0.66

POSITIVE LOGITS

 holes

1.73

 Hole

1.67

 hole

1.66

 Holes

1.64

hole

1.63

Hole

1.59

 HOLE

1.56

Holes

1.53

holes

1.43

HOLE

1.40

Activations Density 0.207%

terms related to holes or openings in various contexts

No Comments

No Known Activations