INDEX

Explanations

terms related to medical treatments and their effects, particularly focusing on anti-epileptic medications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/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.10.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

 esternos

-0.67

 nôtre

-0.59

气氛

-0.56

 VizieR

-0.54

 partecipazione

-0.54

 originaux

-0.54

afficheront

-0.53

 originais

-0.53

jimo

-0.53

tivities

-0.52

POSITIVE LOGITS

 medications

0.80

 medication

0.77

 drugs

0.76

formin

0.73

 drug

0.65

 medicines

0.65

drugs

0.64

cycline

0.64

 meds

0.63

 medicamentos

0.62

Activations Density 0.705%

terms related to medical treatments and their effects, particularly focusing on anti-epileptic medications

No Comments

No Known Activations