INDEX

Explanations

references and citations, particularly publication dates

oai_token-act-pair · gemini-2.0-flash

Citations and references

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

Not in Any Lists

No Comments

Negative Logits

зулта

-0.53

省市镇

-0.50

RegressionTest

-0.49

})$.

-0.48

 frequent

-0.46

infeld

-0.46

 tomorrow

-0.46

))$.

-0.45

[]);

-0.44

 return

-0.44

POSITIVE LOGITS

WriteTagHelper

0.69

FormTagHelper

0.67

اقرأ

0.65

SequentialGroup

0.64

Cyfarwyddwr

0.64

 Normdatei

0.61

ритори

0.60

 Esau

0.57

 PLWABN

0.57

kuuta

0.56

Activations Density 0.701%

references and citations, particularly publication dates

Citations and references

No Comments

No Known Activations