INDEX

Explanations

technical terms and concepts related to computer programming and data structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

-0.67

GIVEREF

-0.65

 anſ

-0.64

يميديا

-0.63

tonode

-0.63

 Jefus

-0.62

GOTREF

-0.62

 للمعارف

-0.62

 ſtate

-0.61

 ſhould

-0.60

POSITIVE LOGITS

 hide

0.28

 ride

0.28

 page

0.28

horizontalLayout

0.28

off

0.28

 сп

0.27

nościo

0.27

 field

0.26

탠

0.26

 worst

0.26

Activations Density 1.049%

technical terms and concepts related to computer programming and data structures

No Comments

No Known Activations