INDEX

Explanations

programming-related keywords and elements associated with code constructs and documentation.

oai_token-act-pair · gpt-4o-mini Triggered by @bot

programming code snippets with specific functions or structures.

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

technical or programming-related terms and syntax elements.

oai_token-act-pair · claude-3-5-sonnet-20240620 Triggered by @bot

Code generation or software version information

np_acts-logits-general · gemini-2.0-flash

copyright ownership and licensing

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.73

The

-0.70

In

-0.69

-0.68

-0.67

An

-0.63

ko

-0.60

-0.58

POSITIVE LOGITS

IndentedString

1.67

 EconPapers

1.60

Autoritní

1.57

Geplaatst

1.55

 beginnetje

1.47

 незавершена

1.47

NameInMap

1.46

GEBURTSDATUM

1.45

 Roskov

1.41

InjectAttribute

1.40

Activations Density 0.361%