INDEX

Explanations

terms related to medical treatments and their effects

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

stopping or decreasing something

np_acts-logits-general · gemini-2.0-flash

preventing reduction or control

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 AssemblyCulture

-0.52

 الحره

-0.46

sidemargin

-0.46

 AssemblyCompany

-0.44

 reembols

-0.44

 comuniques

-0.43

⇝

-0.41

ReusableCell

-0.41

 ConstraintSet

-0.41

mögens

-0.40

POSITIVE LOGITS

 prevention

0.62

 preventing

0.59

 Preventing

0.53

 prevent

0.53

 prevents

0.53

prevention

0.53

 eradicate

0.52

Preventing

0.52

 Prevention

0.51

 eliminating

0.51

Activations Density 0.647%

terms related to medical treatments and their effects

stopping or decreasing something

preventing reduction or control

No Comments

No Known Activations