INDEX

Explanations

adjectives describing quality or condition

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 autorytatywna

-0.51

Aiheesta

-0.50

 těch

-0.50

 behövs

-0.46

 varandra

-0.45

 those

-0.44

 protože

-0.44

Ligações

-0.43

 những

-0.43

 diejenigen

-0.43

POSITIVE LOGITS

 joint

0.57

inheritDoc

0.50

Joint

0.48

 detailed

0.48

 contribution

0.48

 surla

0.48

quelize

0.47

 کش

0.47

 final

0.47

 entire

0.47

Activations Density 0.919%

adjectives describing quality or condition

No Comments

No Known Activations