INDEX

Explanations

technical terms and code-related keywords

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

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_32k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

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

makeConstraints

-0.68

+#+#

-0.64

 resourceCulture

-0.63

mapStateToProps

-0.63

 Reinhold

-0.60

 Púb

-0.60

Portail

-0.59

specialchars

-0.59

newArrayList

-0.58

InvalidProtocol

-0.57

POSITIVE LOGITS

jupiter

4.56

 Jupiter

0.93

Jupiter

0.88

 jupiter

0.79

Pyx

0.74

 оригіналу

0.61

queryInterface

0.58

ος

0.58

TestTools

0.58

FXML

0.56

Activations Density 0.002%

technical terms and code-related keywords

No Comments

No Known Activations