INDEX

Explanations

references to healthcare and related medical topics

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

following "healthcare" or "care"

np_acts-logits-general · gemini-2.0-flash

health care industry and services

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

MigrationBuilder

-0.69

ResponseWriter

-0.65

 sẻ

-0.65

VersionUID

-0.63

맛

-0.58

 Colombie

-0.58

 automatiques

-0.58

 olympique

-0.57

 AttributeSet

-0.57

قایناقلار

-0.57

POSITIVE LOGITS

 industry

0.89

 sector

0.82

 industries

0.69

 services

0.67

 institutions

0.64

 facilities

0.64

 kasarigan

0.62

internalType

0.61

industry

0.61

 providers

0.59

Activations Density 0.346%

references to healthcare and related medical topics

following "healthcare" or "care"

health care industry and services

No Comments

No Known Activations