INDEX

Explanations

structured data related to variables, functions, and their attributes in programming context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 سكانية

-0.72

::::::::

-0.69

StoryboardSegue

-0.65

مصادر

-0.62

 <<<<<<<<<<<<<<

-0.58

SourceChecksum

-0.56

idious

-0.55

Datuak

-0.55

----</

-0.54

εύ

-0.52

POSITIVE LOGITS

 AssemblyCulture

0.84

+#+#

0.68

AsUp

0.67

 препратки

0.59

praš

0.58

انگلیسی

0.55

 دیکھیے

0.54

lė

0.54

ReactDOM

0.53

VIAF

0.53

Activations Density 0.609%

structured data related to variables, functions, and their attributes in programming context

No Comments

No Known Activations