INDEX

Explanations

terms related to statistical estimation and causal models

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

 <<<<<<<<<<<<<<

-0.81

 متعلقه

-0.60

ViewFeatures

-0.58

esteld

-0.57

Välislingid

-0.57

 estekak

-0.57

 accordingly

-0.56

<?

-0.55

XmlAccessorType

-0.55

 fonctionner

-0.55

POSITIVE LOGITS

RenderAtEndOf

0.65

0.64

\#:

0.62

\#:

0.60

 PopupWindow

0.59

0.57

 *)__

0.57

tieth

0.57

脚注の使い方

0.55

"]:

0.53

Activations Density 0.239%

terms related to statistical estimation and causal models

No Comments

No Known Activations