INDEX

Explanations

terms related to medical descriptions and conditions

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

 favors

-0.99

 confiable

-0.97

 theaters

-0.96

 parlor

-0.95

 favorably

-0.95

 flavors

-0.94

 flavorful

-0.90

ighborhood

-0.90

Neighbors

-0.86

 odors

-0.86

POSITIVE LOGITS

Whilst

1.56

 Whilst

1.52

 specialises

1.42

initialise

1.38

 realised

1.38

cognised

1.37

COLOUR

1.36

 realise

1.35

 recognised

1.35

centre

1.34

Activations Density 2.259%

terms related to medical descriptions and conditions

No Comments

No Known Activations