INDEX

Explanations

numerical values associated with inventions or innovations

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

years, dates, and line numbers

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

Vidite

-0.82

AddTagHelper

-0.69

 Chwiliwch

-0.63

 autorytatywna

-0.63

цезда

-0.61

 Италијани

-0.60

contentLoaded

-0.59

SharedDtor

-0.59

 queſta

-0.59



-0.58

POSITIVE LOGITS

The

0.43

the

0.41

0.39

0.38

 subsequent

0.37

0.36

 subsequently

0.35

 voted

0.35

 later

0.35

Activations Density 0.024%

numerical values associated with inventions or innovations

years, dates, and line numbers

No Comments

No Known Activations