INDEX

Explanations

code that includes parentheses or curly braces

oai_token-act-pair · gemini-2.0-flash

programming-related keywords

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

Code-related terms

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

})->

-0.47

libft

-0.47

withOpacity

-0.47

IVEREF

-0.46

Demografie

-0.45

Carriera

-0.44

 мәкалә

-0.44

aan

-0.43

?}",

-0.43

点

-0.43

POSITIVE LOGITS

 propOrder

0.88

DBNull

0.75

yntaxException

0.70

parsedMessage

0.67

ThroughAttribute

0.61

.³

0.61

ViewFeatures

0.60

TargetException

0.59

 DriverManager

0.59

ItemBackground

0.59

Activations Density 0.330%

code that includes parentheses or curly braces

programming-related keywords

Code-related terms

No Comments

No Known Activations