INDEX

Explanations

references to diseases and medical conditions, particularly in the context of research or clinical findings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 AssemblyCulture

-1.23

 Rasp

-1.20

存于互联网档案馆

-1.17

Manbalar

-1.14

Brainz

-1.10

thest

-1.10

 CreateTagHelper

-1.10

 configureStore

-1.10

haustible

-1.08

 prosegu

-1.08

POSITIVE LOGITS

1.87

1.66

1.32

1.29

1.28

1.24

ه

1.19

yny

1.13

er

1.13

en

1.07

Activations Density 2.520%

references to diseases and medical conditions, particularly in the context of research or clinical findings

No Comments

No Known Activations