INDEX

Explanations

references to the concept of a "nation" or "nations."

oai_token-act-pair · gpt-4o-mini

New Auto-Interp

Configuration

chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Architecture

jumprelu

Context Size

1,024

Dataset

chanind/pile-uncopyrighted-gemma-1024-abbrv-1B

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Lourdes

-0.75

Gus

-0.74

Gus

-0.74

 fört

-0.69

Tamb

-0.67

baix

-0.66

間

-0.65

 encom

-0.63

 pinulongan

-0.63

 Tamb

-0.63

POSITIVE LOGITS

 nation

1.23

 Nation

1.23

 nations

1.16

 NATION

1.12

Nation

1.09

 nación

1.08

NATION

1.08

 NATIONS

1.05

 Nations

1.04

nation

1.02

Activations Density 0.007%

references to the concept of a "nation" or "nations."

No Comments

No Known Activations