INDEX

Explanations

structured academic or scientific language

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

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

 initWithFrame

-0.54

πέ

-0.51

UnusedPrivate

-0.48

GEBURTSDATUM

-0.48

裝

-0.47

GenerationType

-0.47

 adipis

-0.46

Hozzáférés

-0.45

 onOptions

-0.45

исленность

-0.45

POSITIVE LOGITS

etc

1.38

etc

1.17

Etc

1.00

 others

0.98

อื่น

0.95

などなど

0.94

usw

0.93

 Others

0.91

Others

0.87

 persino

0.85

Activations Density 0.611%

structured academic or scientific language

No Comments

No Known Activations