INDEX

Explanations

words related to medical and scientific concepts, particularly in the context of antimicrobials and infections

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 universitario

-0.77

 Humphreys

-0.74

 Cyclops

-0.72

깐

-0.70

 Unger

-0.70

Milo

-0.67

 megfelelő

-0.66

 Schubert

-0.65

 SEDS

-0.65

fél

-0.65

POSITIVE LOGITS

Portale

0.96

存于互联网档案馆

0.89

Forrest

0.86

 Forrest

0.81

 Darrell

0.80

 Darn

0.77

Hochspringen

0.76

 Vork

0.76

 Fores

0.75

bootstrapcdn

0.73

Activations Density 7.200%

words related to medical and scientific concepts, particularly in the context of antimicrobials and infections

No Comments

No Known Activations