INDEX

Explanations

references to 'this' and 'self' in programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

Personensuche

-0.71

featureID

-0.69

PerformLayout

-0.59

 theſe

-0.57

CloseOperation

-0.57

httphttps

-0.57

 uſed

-0.56

adaptiveStyles

-0.55

دانشنامهٔ

-0.55

 leſs

-0.53

POSITIVE LOGITS

self

0.42

 self

0.41

me

0.40

 egli

0.40

 Stirn

0.39

voerd

0.39

 meine

0.38

 narrator

0.38

aroa

0.38

weakSelf

0.37

Activations Density 0.077%

references to 'this' and 'self' in programming contexts

No Comments

No Known Activations