INDEX

Explanations

comparison operators and statistical significance indicators in research reports

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

statistical significance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

Дереккөздер

-0.59

⟬

-0.56

ParallelGroup

-0.56

Искәрмәләр

-0.56

HomeAsUpEnabled

-0.54

WithMany

-0.51

 confusión

-0.51

ttemberg

-0.50

Portale

-0.50

 Reſ

-0.50

POSITIVE LOGITS

="@+

0.45

 hampir

0.42

 nearly

0.38

LookAnd

0.38

 almost

0.37

 February

0.35

GenerationType

0.34

alkin

0.32

AccessorTable

0.32

 quase

0.31

Activations Density 0.076%

comparison operators and statistical significance indicators in research reports

statistical significance

No Comments

No Known Activations