INDEX

Explanations

numerical data related to health metrics

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

specific medical terms and concepts related to body functions 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 @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 متعلقه

-0.84

umph

-0.83

Попис

-0.82

Personensuche

-0.81

/**

-0.80

TagMode

-0.80

psies

-0.79

httphttps

-0.78

ureux

-0.78

seamnă

-0.75

POSITIVE LOGITS

 knife

1.00

 Spears

0.98

 stick

0.86

 knives

0.84

 Knife

0.83

Knife

0.81

 Knives

0.80

 sticks

0.79

 Swords

0.78

Needle

0.78

Activations Density 0.327%

numerical data related to health metrics

specific medical terms and concepts related to body functions and conditions

No Comments

No Known Activations