INDEX

Explanations

terms related to healthcare settings and facility names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 disambiguazione

-0.98

 snippetHide

-0.95

 NSCoder

-0.95

ⓧ

-0.79



-0.79

StoryboardSegue

-0.78

 utafitiHapana

-0.74

 Roskov

-0.73

 resourceCulture

-0.72

GeneratedMessage

-0.72

POSITIVE LOGITS

 ward

1.28

ward

1.21

Ward

1.09

 WARD

0.98

 Ward

0.98

 wards

0.95

 forward

0.92

wards

0.91

WARD

0.87

 Forward

0.78

Activations Density 0.084%

terms related to healthcare settings and facility names

No Comments

No Known Activations