INDEX

Explanations

references to updates or changes

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

"update" or a variant of it

np_acts-logits-general · gemini-2.0-flash

software updates

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.58

MLLoader

-0.51

CrossRef

-0.50

 vela

-0.46

تفصیلات

-0.46

llium

-0.45

bourhood

-0.45

ors

-0.44

ход

-0.44

InitStructure

-0.44

POSITIVE LOGITS

mybatisplus

0.77

 EconPapers

0.73

 updater

0.70

 SqlParameter

0.69

basicConfig

0.69

Coucou

0.69

OrCreate

0.68

adaptiveStyles

0.68

mappedBy

0.66

 Paglinawan

0.66

Activations Density 0.104%

references to updates or changes

"update" or a variant of it

software updates

No Comments

No Known Activations