INDEX

Explanations

references to scientific journals and articles

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

Citations with journal information

np_acts-logits-general · gemini-2.0-flash

academic citations

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

OGND

-0.90

AndEndTag

-0.78

SharedDtor

-0.73

 intptr

-0.71

Personensuche

-0.66

 AssemblyProduct

-0.62

URLException

-0.61

πουργ

-0.60

PyExc

-0.58

OptionsMenu

-0.58

POSITIVE LOGITS

Hochspringen

0.51

Билгалдахарш

0.49

 quirúrg

0.45

Izvori

0.45

日閲覧

0.45

ABOR

0.44

RUnlock

0.42

 Fuß

0.42

 Приступљено

0.41

hasOwnProperty

0.41

Activations Density 0.263%

references to scientific journals and articles

Citations with journal information

academic citations

No Comments

No Known Activations