INDEX

Explanations

references to researchers and authors in academic or scholarly contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 BoxFit

-0.69

 كومونز

-0.64

IVEREF

-0.59

recover

-0.58

kose

-0.57

ousands

-0.55

iffance

-0.55

chwitz

-0.55

󠁴

-0.55

ẤT

-0.54

POSITIVE LOGITS

 useRouter

0.58

//

0.52

 cellpadding

0.49

nonatomic

0.49

씨

0.48

IsRequired

0.48

 AsyncTask

0.47

 himself

0.47

 intStringLen

0.47

 astore

0.47

Activations Density 1.108%

references to researchers and authors in academic or scholarly contexts

No Comments

No Known Activations