INDEX

Explanations

terms related to tracking and measurement

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

"Tra" followed by other letters

np_acts-logits-general · gemini-2.0-flash

words starting with Tra

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

<?>>

-0.65

 Keim

-0.61

UnusedPrivate

-0.60

 Hütte

-0.59

 Riproduzione

-0.59

Configurer

-0.58

HTH

-0.57

 AppComponent

-0.57

مصادر

-0.56

Mitar

-0.56

POSITIVE LOGITS

Tra

0.83

tra

0.82

Tra

0.76

tra

0.73

TRA

0.69

TRA

0.61

 тра

0.58

TRACK

0.52

 Тра

0.51

IntoConstraints

0.50

Activations Density 0.084%

terms related to tracking and measurement

"Tra" followed by other letters

words starting with Tra

No Comments

No Known Activations