INDEX

Explanations

terms related to healthcare providers

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

pom

-0.73

 Correa

-0.73

 createSlice

-0.73

haz

-0.72

 calendriers

-0.72

 scanf

-0.71

 Kalam

-0.70

м

-0.69

 JButton

-0.69

Oce

-0.69

POSITIVE LOGITS

 providers

1.23

 provider

1.23

 Provider

1.15

providers

1.11

Provider

1.11

 Providers

1.10

provider

1.09

Providers

1.03

PROVIDER

1.02

 fournisseurs

1.01

Activations Density 0.132%

terms related to healthcare providers

No Comments

No Known Activations