INDEX

Explanations

numerical values and measurements

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

Numbers followed by time units

np_acts-logits-general · gemini-2.0-flash

numbers followed by time units

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 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

 <<<<<<<<<<<<<<

-0.70

gettes

-0.61

autres

-0.60

 exclusives

-0.58

ophores

-0.57

 hashes

-0.56

 milestones

-0.55

 altres

-0.55

Anhalt

-0.55

 jerks

-0.54

POSITIVE LOGITS

 vérit

0.73

 leçons

0.57

 minute

0.57

 prochaines

0.56

 écrans

0.56

 épaules

0.56

0.55

 bénéfices

0.55

 member

0.54

tieth

0.54

Activations Density 0.260%

numerical values and measurements

Numbers followed by time units

numbers followed by time units

No Comments

No Known Activations