INDEX

Explanations

terms related to classification and management processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/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.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

moveToNext

-0.62

PostExecute

-0.60

DotNetBar

-0.55

setLayoutManager

-0.53

ParseException

-0.53

 SwiftUI

-0.52

tagHelperRunner

-0.51

::_('

-0.51

 WaitForSeconds

-0.51

 thyself

-0.51

POSITIVE LOGITS

ongoing

0.59

hyrchwyd

0.51

 ongoing

0.50

 creciente

0.48

ientí

0.47

profession

0.47

الحياه

0.46

growing

0.46

tafel

0.46

continuing

0.45

Activations Density 0.577%

terms related to classification and management processes

No Comments

No Known Activations