INDEX

Explanations

technical jargon related to data handling and messaging systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 ویکی‌پدی

-0.84

:✨

-0.66

 мәкал

-0.64

UnusedPrivate

-0.59

 noDo

-0.59

Tikang

-0.57

ſcher

-0.57

UserScript

-0.56

 imagui

-0.56

 Menſchen

-0.56

POSITIVE LOGITS

 MonoBehaviour

0.40

￡

0.35

levelse

0.35

 geométrico

0.32

 Potencia

0.32

 deuil

0.32

 väg

0.31

 calculées

0.31

 económico

0.31

resizingMask

0.31

Activations Density 0.218%

technical jargon related to data handling and messaging systems

No Comments

No Known Activations