INDEX

Explanations

patterns or labels associated with specific software or data formats, particularly related to 'SL' (presumably ‘slider’)

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 scattata

-0.61

 Ethiopian

-0.57

Демографія

-0.56

 dạ

-0.55

 chives

-0.55

 Saras

-0.55

${(

-0.54

 Everest

-0.52

 Chaldean

-0.50

 Peruvian

-0.50

POSITIVE LOGITS

mand

1.30

 mandate

1.23

 Mandate

1.08

 mandates

1.02

 mand

1.00

 Mand

1.00

########.

0.97

Mand

0.96

 mandated

0.88

Bak

0.87

Activations Density 0.075%

patterns or labels associated with specific software or data formats, particularly related to 'SL' (presumably ‘slider’)

No Comments

No Known Activations