INDEX

Explanations

occurrences of high frequency or notable characters and formatting in documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

CultureInfo

-0.58

 Italijanski

-0.57

#+#

-0.57

ⓧ

-0.56

protoimpl

-0.56

tagext

-0.56

 NgModule

-0.55

 StatelessWidget

-0.53

Initializable

-0.53

LookAnd

-0.52

POSITIVE LOGITS

 становника

0.59

tableFuture

0.59

 vectorielles

0.51

Anyways

0.50

そもそも

0.49

รรม

0.47

 considér

0.47

vesen

0.47

ناك

0.46

Anyhow

0.46

Activations Density 0.025%

occurrences of high frequency or notable characters and formatting in documents

No Comments

No Known Activations