INDEX

Explanations

variable assignments involving "self" in object-oriented programming contexts

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

`self` method calls

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

SpringBootTest

-0.49

 للاسماء

-0.47

casio

-0.47

 ProtoMessage

-0.46

tagPool

-0.45

 BytesLike

-0.44

fast

-0.43

twimg

-0.42

 poffible

-0.40

bur

-0.40

POSITIVE LOGITS

utilisons

0.49

 resourceCulture

0.47

ThroughAttribute

0.39

 mágica

0.39

PreExecute

0.38

 prowadzi

0.37

 Wikiseite

0.37

ltä

0.37

 gravedad

0.37

 clínico

0.37

Activations Density 0.005%

variable assignments involving "self" in object-oriented programming contexts

`self` method calls

No Comments

No Known Activations