INDEX

Explanations

key terms related to programming, deployment, and data manipulation

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

physical connections and states

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

:✨

-0.75

LookAnd

-0.70

featureID

-0.68

DebuggerStep

-0.67

fjspx

-0.66

AddTagHelper

-0.66

RegressionTest

-0.63

KURZBESCHREIBUNG

-0.61

 ligiloj

-0.61

UrlResolution

-0.61

POSITIVE LOGITS

">—

0.35

 defaultstate

0.34

 EXCEPT

0.34

 dışında

0.33

Bibliograf

0.33

 dehors

0.32

setViewportView

0.32

slidesToShow

0.31

MethodManager

0.31

«

0.31

Activations Density 0.126%

key terms related to programming, deployment, and data manipulation

physical connections and states

No Comments

No Known Activations