INDEX

Explanations

phrases related to technical instructions or code context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.38.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

IntoConstraints

-0.49

 bailando

-0.46

TINGS

-0.44

참고

-0.44

 обрабаты

-0.43

 precisione

-0.43

 limpi

-0.43

踊

-0.43

lüğ

-0.43

Semitism

-0.43

POSITIVE LOGITS

การ

0.82

 การ

0.62

 disambiguazione

0.60

 Chwiliwch

0.54

 việc

0.50

 sự

0.48

+#+#

0.43

 bukanlah

0.40

 elaboration

0.39

 Alquiler

0.38

Activations Density 0.069%

phrases related to technical instructions or code context

No Comments

No Known Activations