INDEX

Explanations

code-related keywords and function definitions

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

 ujednoznacz

-0.74

 kaarangay

-0.73

 متعلقه

-0.72

 contextLoads

-0.72

BagLayout

-0.72

 AssemblyCulture

-0.70

AccessorTable

-0.68

BibitemShut

-0.68

 disambiguazione

-0.68

UREAU

-0.66

POSITIVE LOGITS

findOne

0.48

mybatisplus

0.47

findById

0.47

 AspNetCore

0.47

 JpaRepository

0.45

JpaRepository

0.43

 فريبيس

0.43

andReturn

0.43

 hipó

0.43

 rispondere

0.41

Activations Density 0.037%

code-related keywords and function definitions

No Comments

No Known Activations