INDEX

Explanations

scientific terms and specific definitions related to models and assessments

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

:✨

-0.53

锈钢

-0.50

 cherchés

-0.46

 iprot

-0.45

 getItemId

-0.43

 Италијани

-0.42

wußt

-0.41

CompilerServices

-0.41

 Biôgrafia

-0.39

 ffilmiau

-0.38

POSITIVE LOGITS

EndGlobalSection

0.46

/*

0.43

AddWithValue

0.43

뀜

0.40

+#+#

0.40

áss

0.40

 snippetHide

0.40

uzu

0.40

qry

0.39

 Korean

0.38

Activations Density 1.595%

scientific terms and specific definitions related to models and assessments

No Comments

No Known Activations