INDEX

Explanations

instances of the word "begin" and its variations denoting initiation or starting actions

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

begin a new action

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

 únicamente

-0.38

 ciertos

-0.37

indépendance

-0.37

 serupa

-0.37

 similaire

-0.36

 situaciones

-0.34

 separado

-0.33

 tertentu

-0.32

 karar

-0.32

 rayas

-0.32

POSITIVE LOGITS

parsedMessage

0.84

ChildScrollView

0.82

 CreateTagHelper

0.80

 defaultstate

0.80

fjspx

0.79

 Wicidata

0.79

featureID

0.78

 оригіналу

0.77

 nakalista

0.76

tagHelperRunner

0.75

Activations Density 0.035%

instances of the word "begin" and its variations denoting initiation or starting actions

begin a new action

No Comments

No Known Activations