INDEX

Explanations

terms related to data structures and programming objects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

はじめに

-0.62

eleste

-0.59

SOUNDBITE

-0.53

WebElementEntity

-0.50

 kasarigan

-0.49

Red

-0.49

 jScrollPane

-0.47

-0.46

كل

-0.46

 Çünkü

-0.44

POSITIVE LOGITS

 FetchType

0.87

 BoxFit

0.66

 دیکھیے

0.63

 protoimpl

0.62

Bisous

0.61

ſelf

0.60

 transférez

0.60

Tikang

0.58

 xenia

0.57

SBATCH

0.56

Activations Density 0.143%

terms related to data structures and programming objects

No Comments

No Known Activations