INDEX

Explanations

discourse markers and phrases indicating spoken language

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

Follows "he", "she", or "insider"

np_acts-logits-general · gemini-2.0-flash

added to statements

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

SourceChecksum

-0.56

#!/

-0.56

core

-0.53

 Pingback

-0.50

BASELINE

-0.50

 AssemblyCulture

-0.49

 MainAxisSize

-0.49

原始内容存档于

-0.49

 isInitialized

-0.48

bootstrapcdn

-0.48

POSITIVE LOGITS

 added

2.21

 adding

1.95

 adds

1.90

added

1.82

add

1.81

 Added

1.79

 ADDED

1.70

Added

1.69

 Adding

1.67

adding

1.64

Activations Density 0.210%

discourse markers and phrases indicating spoken language

Follows "he", "she", or "insider"

added to statements

No Comments

No Known Activations