INDEX

Explanations

numerical data related to performance metrics or results in competitive contexts

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

following numbers

np_acts-logits-general · gemini-2.0-flash

competed in races and achieved rankings

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-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

рилл

-0.44

Groot

-0.43

dication

-0.43

例句

-0.42

 nghi

-0.42

tis

-0.40

rimento

-0.38

ał

-0.38

集中

-0.38

工具类

-0.38

POSITIVE LOGITS

WithIOException

0.83

 himſelf

0.75

 Theſe

0.75

modelBuilder

0.74

 myſelf

0.73

 itſelf

0.70

 Jefus

0.68

 ſhe

0.67

 deſt

0.65

 tranſ

0.64

Activations Density 0.048%

numerical data related to performance metrics or results in competitive contexts

following numbers

competed in races and achieved rankings

No Comments

No Known Activations