INDEX

Explanations

phrases indicating medical procedures and their implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 purpoſe

-1.15

 Diſ

-1.04

 houſe

-1.01

 poffible

-1.00

 Jefus

-1.00

 fubject

-1.00

 Majefty

-0.97

 ſtate

-0.97

 reaſon

-0.94

 myſelf

-0.93

POSITIVE LOGITS

itemBuilder

0.59

celotti

0.55

 TextAppearance

0.55

0.54

adecimal

0.52

0.51

juvant

0.51

classifiers

0.51

pinMode

0.50

RatingBar

0.49

Activations Density 0.794%

phrases indicating medical procedures and their implications

No Comments

No Known Activations