INDEX

Explanations

technical terms and programming-related concepts

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

AndroidJUnit

-0.79

//</

-0.47

Gambas

-0.47

Билгалдахарш

-0.47

évaluateur

-0.47

 Perſ

-0.47

 enca

-0.47

matchCondition

-0.47

 otomatig

-0.47

المكان

-0.46

POSITIVE LOGITS

RegressionTest

0.53

 zapew

0.40

VYMaps

0.36

styleType

0.35



0.35

 umumnya

0.34

runApp

0.33

forChild

0.33

ardecer

0.33

 suelen

0.33

Activations Density 1.017%

technical terms and programming-related concepts

No Comments

No Known Activations