INDEX

Explanations

mentions of neural networks

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

NN and nn variants

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

']/

-0.52

tyle

-0.51

"]/

-0.50

 BrowserModule

-0.49

IMPORTED

-0.49

 المعيارى

-0.47

BrowserModule

-0.45

هما

-0.45

sstelle

-0.44

 moeite

-0.44

POSITIVE LOGITS

NN

1.05

NN

1.04

nn

0.94

nn

0.93

Nn

0.78

nnn

0.77

xnn

0.77

 Annan

0.73

 Nunn

0.71

enn

0.68

Activations Density 0.004%

mentions of neural networks

NN and nn variants

No Comments

No Known Activations