INDEX

Explanations

formatted or categorized summary or heading elements

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

})*/

-0.72

 invokingState

-0.64

 garçons

-0.64

DockStyle

-0.63

 récents

-0.63

 gebruik

-0.63

 Wikimedijinoj

-0.63

KURZBESCHREIBUNG

-0.62

gunakan

-0.61

 />';

-0.61

POSITIVE LOGITS

 кӀ

0.60

matchCondition

0.50

erapeutic

0.49

losse

0.47

arella

0.46

 nhiêu

0.46

imation

0.45

tività

0.45

openConnection

0.45

 Circ

0.45

Activations Density 0.991%

formatted or categorized summary or heading elements

No Comments

No Known Activations