INDEX

Explanations

references to infections and related pathogens

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

AsUp

-0.77

 varandra

-0.76

 hâte

-0.75

alamus

-0.74

:+:

-0.74

omentos

-0.73

Koo

-0.72

 Owls

-0.71

veratrol

-0.70

NSM

-0.70

POSITIVE LOGITS

 infection

2.05

 infections

1.89

 Infection

1.88

 Infections

1.76

Infection

1.72

infection

1.71

 infected

1.57

 infect

1.50

infected

1.43

 Infected

1.42

Activations Density 0.131%

references to infections and related pathogens

No Comments

No Known Activations