INDEX

Explanations

terms related to pharmaceuticals and pharmacy

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.0.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 autorytatywna

-0.77

 Roskov

-0.76

 utafitiHapana

-0.75

 Jefus

-0.73

 disambiguazione

-0.71

 ItemStack

-0.68

 Audiodateien

-0.68

ſelf

-0.68

 виправивши

-0.68

 itſelf

-0.67

POSITIVE LOGITS

global

0.92

 global

0.91

 Pharma

0.91

Global

0.90

 Global

0.89

Pharma

0.79

 Pharmacy

0.78

 pharma

0.74

 robbed

0.71

 pharmacy

0.70

Activations Density 0.044%

terms related to pharmaceuticals and pharmacy

No Known Activations