INDEX

Explanations

C code related to time calculations

oai_token-act-pair · gemini-2.0-flash

programming language syntax

np_token-act-pair-logits · gpt-4o-mini

zero

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Lähteet

-0.94

енча

-0.82

 للاسماء

-0.82

 الرياضيه

-0.80

 فريبيس

-0.80

 חיצוניים

-0.78

Jeografia

-0.77

RegressionTest

-0.77

 незавершена

-0.75

DoubleQuotes

-0.75

POSITIVE LOGITS

Dec

0.41

openqa

0.41

 Haupts

0.39

 thực

0.37

 chiusura

0.36

nsec

0.36

0.35

 Wirk

0.35

Activations Density 4.687%

C code related to time calculations

programming language syntax

zero

No Comments

No Known Activations