INDEX

Explanations

technical terms related to medical processes and outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

__(/*!

-0.75

balleur

-0.67

 оригіналу

-0.58

ativement

-0.50

GIVEREF

-0.48

InjectAttribute

-0.48

#+#

-0.47

__*/

-0.46

ۖ

-0.46

รรม

-0.45

POSITIVE LOGITS

 post

4.33

post

3.89

 Post

3.87

Post

3.75

 POST

3.14

POST

2.90

 posts

2.86

 пост

2.62

 Posts

2.58

posts

2.52

Activations Density 0.207%

technical terms related to medical processes and outcomes

No Comments

No Known Activations