INDEX

Explanations

statistical analysis of sampled data, looking for errors, deviations, and significance

oai_token-act-pair · gemini-2.0-flash

this neuron activates for արտադրանք

np_token-act-pair-logits · gemini-2.0-flash

statistical errors

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ní

-0.49

 publiée

-0.49

不足

-0.49

atitis

-0.48

shadowOpacity

-0.47

ритори

-0.47

 tolerances

-0.46

ัต

-0.46

STRUCTIONS

-0.46

发表于

-0.45

POSITIVE LOGITS

 متعلقه

0.70

 nahilalakip

0.62

findpost

0.61

 دیکھیے

0.59

లాలు

0.59

inose

0.59

rungsseite

0.58

abestanden

0.54

kloped

0.53

afficheront

0.53

Activations Density 6.881%

statistical analysis of sampled data, looking for errors, deviations, and significance

this neuron activates for արտադրանք

statistical errors

No Comments

No Known Activations