INDEX

Explanations

references to healthcare and medical terminology

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

TypedDataSet

-0.89

 EconPapers

-0.74

 مرئيه

-0.74

 defaultstate

-0.72

 Chwiliwch

-0.71

########.

-0.71

WebVitals

-0.70

SequentialGroup

-0.70

 linkovi

-0.69

IContainer

-0.68

POSITIVE LOGITS

ized

0.51

 device

0.45

mari

0.43

stoj

0.41

 mari

0.41

0.40

вер

0.40

vol

0.39

 Mari

0.39

 Straß

0.39

Activations Density 0.110%

references to healthcare and medical terminology

No Comments

No Known Activations