INDEX

Explanations

terms and phrases related to nuclear energy, reactors, and waste management

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

tire

-0.51

onavir

-0.50

mapbox

-0.50

Tre

-0.49

Jeografia

-0.48

 آس

-0.48

eqn

-0.47

 Marca

-0.45

kháu

-0.45

ixel

-0.45

POSITIVE LOGITS

 nucléaire

1.04

 nuclear

1.01

 Nuclear

0.92

Nuclear

0.88

 nuclé

0.85

nuclear

0.84

 NUCLEAR

0.82

 uranium

0.82

 reactors

0.79

 Uranium

0.78

Activations Density 0.758%

terms and phrases related to nuclear energy, reactors, and waste management

No Comments

No Known Activations