INDEX

Explanations

references to previous experiences and evaluations of products or services

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

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_1m/average_l0_107

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

1,048,576

Data Type

float32

Hook Name

blocks.12.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

 intptr

-0.77

 utafitiHapana

-0.70

 nahilalakip

-0.65

 المعيارى

-0.62

 cherchés

-0.62

 EconPapers

-0.62

(!__

-0.60

CppMethod

-0.59

 useAppContext

-0.58

 متعلقه

-0.57

POSITIVE LOGITS

 pengar

0.52

GoogleMap

0.51

berley

0.51

ounced

0.50

yntaxException

0.50

 DEAL

0.48

AILABILITY

0.48

arrings

0.48

haviour

0.48

 rada

0.47

Activations Density 0.009%

references to previous experiences and evaluations of products or services

No Comments

No Known Activations