INDEX

Explanations

references to animals and their environments, as well as scientific terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

AndEndTag

-0.69

Välislingid

-0.68

NKC

-0.65

 Normdatei

-0.63

ConstraintMaker

-0.62

GOTREF

-0.61

 kyse

-0.59

 urma

-0.58

šanai

-0.57

 estekak

-0.57

POSITIVE LOGITS

/***/

0.62

 LoggerFactory

0.60

Manbalar

0.57

BindView

0.54

참고

0.54

tonode

0.52

:][

0.50

[*]

0.50

forKey

0.48

RTLD

0.48

Activations Density 0.434%

references to animals and their environments, as well as scientific terminology

No Comments

No Known Activations