INDEX

Explanations

the article "a" and words associated with taking action or making decisions

oai_token-act-pair · gemini-2.0-flash

Article "a"

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

AutoScale

-0.65

 kasarigan

-0.62

ViewFeatures

-0.61

HasBeenSet

-0.56

 doInBackground

-0.55

 Take

-0.49

Take

-0.48

ThroughAttribute

-0.48

abestanden

-0.48

 takes

-0.47

POSITIVE LOGITS

 disambiguazione

0.89

Efq

0.62

canestro

0.57

 perſon

0.55

 Aéroport

0.55

 whoſe

0.54

 itſelf

0.54

 {}),

0.54

 Cæsar

0.53

 SNES

0.53

Activations Density 2.995%

the article "a" and words associated with taking action or making decisions

Article "a"

No Known Activations