INDEX

Explanations

specific terminology related to scientific research and concepts

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

Preceding Q or District or following "has"

np_acts-logits-general · gemini-2.0-flash

generally applicable statements

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

SequentialGroup

-0.62

tagext

-0.59

etCode

-0.54

DockStyle

-0.53

まるで

-0.51

 sánh

-0.51

Lähteet

-0.51

 referenties

-0.50

 Просто

-0.50

 Ανακτήθηκε

-0.50

POSITIVE LOGITS

 generally

1.02

 usually

0.96

 typically

0.94

 notoriously

0.89

generally

0.85

 normally

0.83

 costuma

0.80

 ordinarily

0.78

 suele

0.75

 généralement

0.74

Activations Density 0.587%

specific terminology related to scientific research and concepts

Preceding Q or District or following "has"

generally applicable statements

No Comments

No Known Activations