INDEX

Explanations

references to healthcare-related topics

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 onResume

-0.52

 hereof

-0.51

 excise

-0.50

CompoundButton

-0.48

ainville

-0.47

gefü

-0.47

Delayed

-0.47

 Edson

-0.47

 requestCode

-0.46

 patch

-0.46

POSITIVE LOGITS

enterOuterAlt

0.86

 Anſ

0.83

 Reſ

0.82

 Baskets

0.78

 Bask

0.75

AndroidJUnit

0.74

 healthcare

0.73

Enter

0.72

 Bernadette

0.71

 propOrder

0.71

Activations Density 0.074%

references to healthcare-related topics

No Comments

No Known Activations