INDEX

Explanations

structured comments in code documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

principalTable

-0.50

QMetaType

-0.49

setViewName

-0.49

iores

-0.47

ഔ

-0.46

AsUp

-0.45

sedown

-0.45

setSelection

-0.44

ViewFeatures

-0.43

rania

-0.42

POSITIVE LOGITS

AnimationsModule

0.73

出版年

0.66

 chré

0.60

 Schilling

0.59

Посилання

0.58

EDEFAULT

0.57

AccessorTable

0.57

atimes

0.56

Initializable

0.55

Quellen

0.54

Activations Density 0.044%

structured comments in code documentation

No Comments

No Known Activations