INDEX

Explanations

statistical terms and indicators related to analysis and significance in research studies

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

Follows "was," "be," or "is"

np_acts-logits-general · gemini-2.0-flash

state of completion

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

EndInit

-0.47

TestBed

-0.45

 transfieras

-0.42

ylabel

-0.42

ская

-0.41

MigrationBuilder

-0.40

OGND

-0.39

 Préférences

-0.39

Paginator

-0.39

PerformLayout

-0.39

POSITIVE LOGITS

 achieved

1.19

 accomplished

1.06

achieved

0.93

 accomplish

0.89

 achieve

0.89

complished

0.85

 attained

0.81

 achieves

0.81

 conveyed

0.78

achieve

0.77

Activations Density 0.785%

statistical terms and indicators related to analysis and significance in research studies

Follows "was," "be," or "is"

state of completion

No Comments

No Known Activations