INDEX

Explanations

code-related syntax, specifically function declarations and template specifications

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

code keywords and declarations

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

 Italijanski

-0.46

providedIn

-0.35

<eos>

-0.34

 variar

-0.31

 continue

-0.31

 rather

-0.31

Continuar

-0.31

stateMutability

-0.31

cjonal

-0.31

 Numerade

-0.31

POSITIVE LOGITS

MessageOf

0.64

RTEX

0.56

="@+

0.54

AndEndTag

0.53

 autorytatywna

0.52

ंदीखरीदारी

0.48

 للاسماء

0.47

PRWEB

0.47

 CURIAM

0.47

monton

0.46

Activations Density 0.065%

code-related syntax, specifically function declarations and template specifications

code keywords and declarations

No Comments

No Known Activations