INDEX

Explanations

programming or coding-related terminology

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

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Tikang

-0.47

 Exacts

-0.40

balleur

-0.38

Referências

-0.37

 disambiguazione

-0.36

 EconPapers

-0.36

 jLabel

-0.35

 surla

-0.34

الدراسه

-0.34

homonymie

-0.34

POSITIVE LOGITS

 PowerShell

0.81

0.55

enumii

0.52

/**

0.52

CppMethod

0.50

jsii

0.50

yargs

0.49

NewGuid

0.49

IntoConstraints

0.48

toPromise

0.48

Activations Density 0.009%

programming or coding-related terminology

No Comments

No Known Activations