INDEX

Explanations

references to numerical data or statistics

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

numerical data and parentheses

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

percentages and units

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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

 которое

-0.47

ต่างๆ

-0.45

vité

-0.44

who

-0.43

 nào

-0.43

 چیست

-0.42

 który

-0.42

 loved

-0.42

viembre

-0.41

有哪些

-0.41

POSITIVE LOGITS

 nahilalakip

1.08

Geplaatst

0.99

 Савезне

0.92

 roughly

0.89

 equivalent

0.88

equivalent

0.86

roughly

0.83

WillAppear

0.83

oredCriteria

0.83

脚注の使い方

0.82

Activations Density 0.201%

references to numerical data or statistics

numerical data and parentheses

percentages and units

No Comments

No Known Activations