INDEX

Explanations

phrases emphasizing significant aspects or characteristics of a topic

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_15/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.15.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

raulic

-0.62

 AssemblyCompany

-0.55

 useRouter

-0.54

 liever

-0.52

transQ

-0.49

\{\\

-0.49

yntaxException

-0.48

ctez

-0.47

 onPostExecute

-0.46

instellungen

-0.45

POSITIVE LOGITS

 AssemblyCulture

0.46

 Shout

0.38

Среди

0.33

webElementXpaths

0.33

 regularmente

0.33

有一个

0.32

的重要

0.32

enderror

0.31

什么事

0.30

役

0.30

Activations Density 0.397%

phrases emphasizing significant aspects or characteristics of a topic

No Comments

No Known Activations

phrases emphasizing significant aspects or characteristics of a topic

No Comments

No Known Activations