INDEX

Explanations

key performance indicators related to health, activity, and voting

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 "..\..\

-0.56

 miniaturka

-0.51

 diſt

-0.51

 Wicidata

-0.45

 ſtate

-0.44

 "..\..\..\

-0.44

 bocas

-0.43

 ſta

-0.41

 besos

-0.41

établir

-0.40

POSITIVE LOGITS

:✨

1.17

Personensuche

0.59

Personendaten

0.54

 Commencez

0.53

 BoxFit

0.52

writeFieldEnd

0.49

 оригіналу

0.47

 lenker

0.46

oredCriteria

0.43

GEBURTSDATUM

0.43

Activations Density 0.003%

key performance indicators related to health, activity, and voting

No Comments

No Known Activations