INDEX

Explanations

punctuation marks and numerical values

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.39.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

п

-0.42

и

-0.42

pantalón

-0.41

А

-0.41

в

-0.39

В

-0.38

 otomatig

-0.38

а

-0.38

С

-0.38

brinco

-0.37

POSITIVE LOGITS

parsedMessage

0.57

ImageContext

0.54

بوابة

0.50

Gön

0.48

crí

0.44

RTEE

0.43

 adelantado

0.43

 atracción

0.43

MessageState

0.43

Portail

0.43

Activations Density 0.037%

punctuation marks and numerical values

No Comments

No Known Activations