INDEX

Explanations

expressions involving mathematical notation or variables

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

RegressionTest

-0.94

 تضيفلها

-0.84

protoimpl

-0.71

adaptiveStyles

-0.65

IZONT

-0.63

(;;)

-0.62

XmlAccessorType

-0.61

NavigationView

-0.60

sizeCache

-0.59

LookAnd

-0.59

POSITIVE LOGITS

bf

0.65

 numberOfRows

0.61

rm

0.58

cal

0.56

{\

0.55

 Faithful

0.55

${\

0.55

={\

0.54

sl

0.54

em

0.52

Activations Density 0.584%

expressions involving mathematical notation or variables

No Comments

No Known Activations