INDEX

Explanations

references to various sheet-type documents and organizational tools

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

sheet planner

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

 Propag

-0.47

✨:

-0.46

onOptions

-0.46

 betrokken

-0.46

 konden

-0.44

 brinquedos

-0.44

 potência

-0.43

)»

-0.43

 către

-0.43

 mogen

-0.43

POSITIVE LOGITS

Sheet

1.24

 Sheet

1.21

 sheet

1.20

 SHEET

1.15

 Sheets

1.02

SHEET

1.00

sheet

0.98

heet

0.97

 sheets

0.94

Sheets

0.94

Activations Density 0.006%

references to various sheet-type documents and organizational tools

sheet planner

No Comments

No Known Activations