INDEX

Explanations

entities and terms related to medical conditions and treatment processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 iconTwitter

-0.66

 myſelf

-0.66

存于互联网档案馆

-0.64

protoimpl

-0.63

 AspNetCore

-0.60

 coû

-0.59

 iyon

-0.57

PhysRevD

-0.56

 themſelves

-0.56

 ſta

-0.56

POSITIVE LOGITS

<bos>

0.69

 GenerationType

0.62

djangoproject

0.60

0.59

”

0.54

PreAuthorize

0.53

انيف

0.53

PickerController

0.52

 Meksiku

0.51

</em>

0.51

Activations Density 0.847%

entities and terms related to medical conditions and treatment processes

No Comments

No Known Activations