INDEX

Explanations

phrases that express uncertainty or questions about medical guidelines and practices

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

Quoted speech and experts

np_acts-logits-general · gemini-2.0-flash

experts and scholars

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 defaultstate

-0.49

AutoScaleMode

-0.45

iettivo

-0.44

 myſelf

-0.43

ysaccharides

-0.43

-0.40

хьтан

-0.39

 betweenstory

-0.39

ysaccharide

-0.39

DidLoad

-0.38

POSITIVE LOGITS

 experts

0.79

 expert

0.77

expert

0.71

 Experts

0.65

 Expert

0.65

Experts

0.65

 экспер

0.64

 expertos

0.61

 esperti

0.60

Expert

0.60

Activations Density 0.143%

phrases that express uncertainty or questions about medical guidelines and practices

Quoted speech and experts

experts and scholars

No Comments

No Known Activations