INDEX

Explanations

medical-related symptoms, particularly unexplained somatic symptoms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 myſelf

-1.41

 Theſe

-1.27

 photolibrary

-1.24

 Jefus

-1.23

 Reſ

-1.22

 ―――――

-1.20

Efq

-1.17

 fevere

-1.16

 itſelf

-1.16

 leaſt

-1.15

POSITIVE LOGITS

 semantic

0.68

0.63

0.61

0.58

 Semantic

0.58

Actual

0.58

cn

0.55

0.54

semantic

0.54

0.53

Activations Density 0.118%

medical-related symptoms, particularly unexplained somatic symptoms

No Comments

No Known Activations