INDEX

Explanations

terms that indicate statistical significance in research

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

"significant" followed by quantities or changes

np_acts-logits-general · gemini-2.0-flash

significant measured changes

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

au

-0.48

-0.47

 AdapterView

-0.45

PreAuthorize

-0.44

createQuery

-0.44

CppCodeGen

-0.40

sidemargin

-0.40

Décès

-0.40

herin

-0.39

کرد

-0.39

POSITIVE LOGITS

 amount

0.99

 amounts

0.87

 improvement

0.87

 difference

0.86

 differences

0.85

 Improvement

0.82

 improvements

0.81

improvement

0.80

amount

0.79

 >=",

0.79

Activations Density 0.214%

terms that indicate statistical significance in research

"significant" followed by quantities or changes

significant measured changes

No Comments

No Known Activations