INDEX

Explanations

code-related terminology and structures, particularly in programming contexts

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 فريبيس

-0.68

Personendaten

-0.55

 Gesch

-0.40

zet

-0.40

httphttps

-0.39

Aholisi

-0.38

зайн

-0.38

niosek

-0.38

enderror

-0.37

 shout

-0.37

POSITIVE LOGITS

 snippetHide

0.56

UnitTesting

0.54

evos

0.49

 AssemblyProduct

0.48

 defStyleAttr

0.47

 JADX

0.46

 ✭✭

0.45

 webdriver

0.45

randomUUID

0.45

Portail

0.42

Activations Density 0.149%

code-related terminology and structures, particularly in programming contexts

No Comments

No Known Activations