INDEX

Explanations

code-related comments and class definitions in programming documentation

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

AWS CloudFormation URLs and documentation

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

parsedMessage

-0.73

 disambiguazione

-0.71

+#+#

-0.69

 виправивши

-0.67

الحياه

-0.67

الدراسه

-0.66

GEBURTSDATUM

-0.66

Hentet

-0.62

Datuak

-0.62

softc

-0.62

POSITIVE LOGITS

 available

0.35

True

0.33

Inter

0.33

you

0.32

Push

0.32

inst

0.31

Compat

0.31

CR

0.31

 Inter

0.30

 prawda

0.30

Activations Density 0.017%

code-related comments and class definitions in programming documentation

AWS CloudFormation URLs and documentation

No Comments

No Known Activations