INDEX

Explanations

quantitative measurements and scaling factors in a scientific context

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

"By" followed by quantities or amounts

np_acts-logits-general · gemini-2.0-flash

factors and ratios

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

APORE

-0.54

gbaar

-0.54

MetaObject

-0.45

 preferências

-0.44

IMDb

-0.44

harap

-0.43

▾

-0.41

rmtree

-0.41

 veterin

-0.40

jude

-0.40

POSITIVE LOGITS

 factor

2.27

factor

2.03

 Factor

1.91

Factor

1.86

 factors

1.83

 FACTOR

1.75

 faktor

1.63

factors

1.62

 Factors

1.62

FACTOR

1.59

Activations Density 0.772%

quantitative measurements and scaling factors in a scientific context

"By" followed by quantities or amounts

factors and ratios

No Comments

No Known Activations