INDEX

Explanations

references to prime numbers and prime ministers

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

 Fanny

-0.90

Fanny

-0.88

 Josie

-0.83

 guste

-0.73

"]=

-0.70

../

-0.68

chafft

-0.68

исп

-0.67

 Burroughs

-0.67

attery

-0.66

POSITIVE LOGITS

 PRIME

1.20

 Prime

1.16

PRIME

1.10

Primes

1.08

 primes

1.06

primes

1.05

 समीक्षाओं

0.99

 prime

0.96

Prime

0.96

 facie

0.95

Activations Density 0.111%

references to prime numbers and prime ministers

No Comments

No Known Activations