INDEX

Explanations

important acronyms or abbreviations relevant to various fields

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

Abbreviations and acronyms

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.24.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

 impreso

-0.45

 chiesto

-0.43

 personlig

-0.42

 régulier

-0.42

 متن

-0.41

 aislado

-0.39

 assise

-0.39

 widok

-0.38

 abstrato

-0.38

 aislados

-0.36

POSITIVE LOGITS

XmlAccessorType

0.67

CppMethod

0.64

UnusedPrivate

0.60

findpost

0.57

 nakalista

0.55

Kam

0.54

providedIn

0.53

cam

0.53

 doInBackground

0.52

.*")]

0.52

Activations Density 0.147%

important acronyms or abbreviations relevant to various fields

Abbreviations and acronyms

No Comments

No Known Activations