INDEX

Explanations

terms related to medical diagnostics and techniques

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/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.14.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

CloseOperation

-0.98

AutoScale

-0.91

Personendaten

-0.90

Portale

-0.89

GEBURTSDATUM

-0.83

arithmic

-0.82

archiviato

-0.81

 Италијани

-0.80

 ویکی‌پدیا

-0.79

IGraphics

-0.78

POSITIVE LOGITS

0.55

жи

0.53

of

0.49

0.45

kund

0.45

es

0.45

0.44

ons

0.43

otu

0.43

iche

0.42

Activations Density 0.353%

terms related to medical diagnostics and techniques

No Comments

No Known Activations