INDEX

Explanations

syntax elements and punctuation used in programming or code

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

 للمعارف

-0.85

 فريبيس

-0.84

AndEndTag

-0.83

 AssemblyCompany

-0.79

 ―――――

-0.71

 disambiguazione

-0.69

Personensuche

-0.69

AnchorStyles

-0.69

ſicht

-0.66

ReusableCell

-0.66

POSITIVE LOGITS

 Hongrie

0.33

 include

0.31

vœ

0.30

 Clark

0.30

 Lebe

0.28

カ

0.28

 moins

0.28

 âge

0.28

Activations Density 0.006%

syntax elements and punctuation used in programming or code

No Comments

No Known Activations