INDEX

Explanations

technical terms and comparisons related to performance metrics in data processing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

extendable

-0.54

 noDo

-0.54

Hozzáférés

-0.53

ibol

-0.52

³)

-0.52

öffentlichungen

-0.52

حياته

-0.51

 veget

-0.51

–)

-0.51

 judiciales

-0.51

POSITIVE LOGITS

 Савезне

0.58

 Vikipedi

0.55

protoimpl

0.53

 alike

0.52

racene

0.52

niająca

0.51

etc

0.50

etc

0.49

EnableWeb

0.49

rativa

0.49

Activations Density 1.632%

technical terms and comparisons related to performance metrics in data processing

No Comments

No Known Activations