INDEX

Explanations

pieces of code and programming language syntax

oai_token-act-pair · gemini-2.0-flash

Code and programming

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

ر

-0.40

薩

-0.38

ف

-0.38

olon

-0.37

inhua

-0.36

ج

-0.36

Obrázky

-0.36

 Holman

-0.36

ר

-0.36

ها

-0.36

POSITIVE LOGITS

featureID

0.91

principalColumn

0.79

 BrowserModule

0.77

 blockSize

0.77

 serviceName

0.73

 methodName

0.71

 numberOf

0.71

 maxSize

0.69

 fileSize

0.69

 phoneNumber

0.68

Activations Density 10.991%

pieces of code and programming language syntax

Code and programming

No Comments

No Known Activations