INDEX

Explanations

references to specific scientific papers or datasets

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

webElementXpaths

-0.89

rungsseite

-0.83

 Wikimedijinoj

-0.81

parsedMessage

-0.80

Personendaten

-0.78

:✨

-0.74

@"/

-0.73

WebElementEntity

-0.72

Portail

-0.70

ьаж

-0.70

POSITIVE LOGITS

 htons

0.58

VIAF

0.51

crit

0.49

 JURIS

0.47

thum

0.46

 ballads

0.46

 quadru

0.46

 Sigism

0.45

 Viitattu

0.45

莫

0.45

Activations Density 0.104%

references to specific scientific papers or datasets

No Comments

No Known Activations