INDEX

Explanations

key moments and specific incidents in narratives, particularly those tied to emotional or significant events

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

出版年

-0.64

 zuges

-0.54

Tracce

-0.48

 partout

-0.48

]<<"

-0.48

posit

-0.47

PreferredItem

-0.47

ებ

-0.47

]=>

-0.46

Gatt

-0.46

POSITIVE LOGITS

那天

0.68

 accidente

0.66

 night

0.63

ครั้ง

0.63

 '\\;'

0.60

 incident

0.60

帖最后由

0.57

hdashline

0.57

nacht

0.57

 moment

0.57

Activations Density 0.523%

key moments and specific incidents in narratives, particularly those tied to emotional or significant events

No Comments

No Known Activations