INDEX

Explanations

proper nouns and names related to people, places, and organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 Fide

-0.80

 Roskov

-0.76

 Visser

-0.73

mij

-0.73

 Adri

-0.71

 Arad

-0.70

Mij

-0.70

 Mire

-0.65

<em>

-0.64

Mire

-0.63

POSITIVE LOGITS

 Inverness

1.10

CMA

0.92

 Berthe

0.92

Kau

0.90

Kau

0.88

 Chun

0.87

SCO

0.87

 paral

0.86

 Folsom

0.85

 Erasmus

0.84

Activations Density 1.562%

proper nouns and names related to people, places, and organizations

No Comments

No Known Activations