INDEX

Explanations

references to figures and numerical values in scientific documents

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

Code or file paths

np_acts-logits-general · gemini-2.0-flash

code and science"}, "technical terms and research"}

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

OK

-0.52

-0.51

 presente

-0.49

ok

-0.48

co

-0.48

-0.47

vario

-0.47

-0.46

 Universal

-0.46

-0.45

POSITIVE LOGITS

bootstrapcdn

0.88

Efq

0.84

ArgsConstructor

0.81

 ―――――

0.79

 InputDecoration

0.76

 XNUMX

0.74

 varandra

0.74

^(@)

0.74

StackNavigator

0.74

 Baillargeon

0.73

Activations Density 0.445%

references to figures and numerical values in scientific documents

Code or file paths

code and science"}, "technical terms and research"}

No Comments

No Known Activations