INDEX

Explanations

lines of code defining variables, especially ones starting with "IP," "IFT", ending with an abbreviation in all caps, and assigning a hexadecimal value

oai_token-act-pair · gemini-2.0-flash

Code

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

<bos>

-1.25

хьтан

-1.02

RegressionTest

-0.99

contentLoaded

-0.85

TypedDataSet

-0.85

 Савезне

-0.84

 <=",

-0.83

Geplaatst

-0.81

 Мексичка

-0.80

Personensuche

-0.79

POSITIVE LOGITS

ULAR

0.52

ERY

0.47

ERIA

0.46

fton

0.44

 كومونز

0.42

gged

0.41

bid

0.41

uler

0.41

 egli

0.41

LECT

0.40

Activations Density 37.673%

lines of code defining variables, especially ones starting with "IP," "IFT", ending with an abbreviation in all caps, and assigning a hexadecimal value

Code

No Comments

No Known Activations

lines of code defining variables, especially ones starting with "IP," "IFT", ending with an abbreviation in all caps, and assigning a hexadecimal value

Code

No Comments

No Known Activations