INDEX

Explanations

mentions of probability, especially those surrounding drawing without replacement

oai_token-act-pair · gemini-2.0-flash

Jam

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 समीक्षक

-0.76

RectangleBorder

-0.72

 EconPapers

-0.69

PhysRevD

-0.66

findpost

-0.63

Datuak

-0.63

 abgerufen

-0.60

 باخ

-0.57

webElementGuid

-0.56

 bezeichneter

-0.55

POSITIVE LOGITS

uzi

0.50

خة

0.50

athyroid

0.50

XAxis

0.48

ropolitana

0.47

 webdriver

0.47

PreferredItem

0.45

UAWEI

0.45

strix

0.45

jooq

0.44

Activations Density 0.689%

mentions of probability, especially those surrounding drawing without replacement

Jam

No Comments

No Known Activations