INDEX

Explanations

references to software packages and licenses

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 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

er

-0.63

 NSCoder

-0.59

ed

-0.59

 makita

-0.57

Хьажоргаш

-0.56

 disambiguazione

-0.55

 jongen

-0.54

 Maryam

-0.53

ย

-0.53

brigens

-0.53

POSITIVE LOGITS

package

2.06

subpackage

0.95

 AssemblyTitle

0.90

namespace

0.79

 packageName

0.79

packageName

0.78

PACKAGE

0.72

MENAFN

0.71

BaseAdapter

0.69

))))))))

0.67

Activations Density 0.059%

references to software packages and licenses

No Comments

No Known Activations