INDEX

Explanations

terms associated with medical conditions and their symptoms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

RefNanny

-0.70

 firebaseConfig

-0.61

HasForeignKey

-0.60

findpost

-0.59

Naissance

-0.58

談社

-0.54

 taglio

-0.54

كويكب

-0.54

 متعلقه

-0.54

POSITIVE LOGITS

 filling

0.65

 clogged

0.58

RuleContext

0.57

 clogging

0.56

jam

0.56

 fill

0.56

filling

0.55

 overrun

0.55

whel

0.54

 Filling

0.54

Activations Density 0.518%

terms associated with medical conditions and their symptoms

No Comments

No Known Activations