INDEX

Explanations

key terms and phrases associated with significant social and political topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 forcément

-0.55

 cela

-0.51

 estric

-0.51

 nécessairement

-0.50

 įva

-0.50

 parfaite

-0.50

 estrictamente

-0.49

ExtendWith

-0.49

 sempurna

-0.49

 parfois

-0.48

POSITIVE LOGITS

 major

0.90

#+#

0.88

MAJOR

0.84

 utama

0.83

########.

0.83

 principali

0.83

major

0.81

 principales

0.80

 nahilalakip

0.79

 main

0.78

Activations Density 0.512%

key terms and phrases associated with significant social and political topics

No Comments

No Known Activations