INDEX

Explanations

references to studies or documented research sources

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

 betweenstory

-0.62

 EconPapers

-0.60

Життєпис

-0.54

kháu

-0.54

Cyfeiriadau

-0.53

EndGlobalSection

-0.53

Hochspringen

-0.52

 ویکی‌پدیا

-0.51

lugin

-0.51

InjectAttribute

-0.50

POSITIVE LOGITS

(@"%@",

0.58

 Pressure

0.56

ViewInit

0.52

Parcelize

0.52

]<<

0.51

 Wilber

0.51

 áll

0.49

 Liner

0.49

 amus

0.48

liner

0.47

Activations Density 1.124%

references to studies or documented research sources

No Comments

No Known Activations