INDEX

Explanations

medical and scientific terminology related to research methodologies and health studies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

 Ее

-0.84

 gants

-0.81

Theater

-0.80

theater

-0.77

 theater

-0.77

armor

-0.76

 theaters

-0.72

 nationaux

-0.71

VIAF

-0.70

ighborhood

-0.70

POSITIVE LOGITS

 fibres

1.53

 programmes

1.44

 colours

1.44

 utilisation

1.42

 optimisation

1.41

 honour

1.41

 organisations

1.41

 travellers

1.40

 licences

1.40

 tumours

1.40

Activations Density 0.294%

medical and scientific terminology related to research methodologies and health studies

No Comments

No Known Activations