INDEX

Explanations

patterns and classifications related to 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 @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/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.19.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

 anſ

-0.64

 purpoſe

-0.63

 Anſ

-0.57

Piv

-0.56

 benchmarking

-0.55

 juſ

-0.54

 Shear

-0.54

 raiſ

-0.54

 houſe

-0.53

 kios

-0.53

POSITIVE LOGITS

 disease

0.62

 causing

0.60

 patients

0.60

 caused

0.59

 chez

0.58

 disorders

0.57

 발생

0.57

 diseases

0.56

 causes

0.56

 aggravate

0.55

Activations Density 0.593%

patterns and classifications related to medical conditions and their symptoms

No Comments

No Known Activations