INDEX

Explanations

technical terms and concepts related to programming and system architecture

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

function, device, item, processes, into, expiration, answer

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

ftagPool

-0.93

 Normdatei

-0.92

 AssemblyCulture

-0.92

Personendaten

-0.91

 мәкал

-0.90

+#+#

-0.86

 MainAxisSize

-0.83

AndEndTag

-0.83

səhifə

-0.80

RegressionTest

-0.79

POSITIVE LOGITS

 möge

0.32

 regular

0.31

regular

0.29

 Ordnung

0.29

 teş

0.28

 Einheiten

0.28

 congrès

0.28

Regular

0.27

 Preferably

0.26

Activations Density 0.050%

technical terms and concepts related to programming and system architecture

function, device, item, processes, into, expiration, answer

No Comments

No Known Activations