INDEX

Explanations

numerical data and statistics

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

numbers in scientific contexts

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

 يتيمه

-0.38

mon

-0.37

nities

-0.34

Przypisy

-0.33

erevan

-0.32

IntoConstraints

-0.32

ments

-0.32

 مت

-0.31

EMON

-0.31

پل

-0.31

POSITIVE LOGITS

ItemBackground

0.80

:✨

0.59

PreferredItem

0.59

InputBorder

0.57

 nakalista

0.56

帖最后由

0.55

audiovisuel

0.55

mergeFrom

0.54

 NSCoder

0.54

 Comunicação

0.53

Activations Density 0.003%

numerical data and statistics

numbers in scientific contexts

No Comments

No Known Activations