INDEX

Explanations

code-related commands and syntax in programming contexts

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

File paths and directories

np_acts-logits-general · gemini-2.0-flash

project file paths

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 المعيارى

-0.67

 للمعارف

-0.60

ThroughAttribute

-0.59

 متعلقه

-0.56

NewUrlParser

-0.56

principalColumn

-0.55

writeFieldEnd

-0.54

قایناق‌لار

-0.53

DeleteBehavior

-0.53

ISupport

-0.53

POSITIVE LOGITS

src

1.05

src

1.00

README

0.86

../

0.80

./

0.80

../

0.80

../../

0.78

 README

0.77

 assets

0.76

LICENSE

0.75

Activations Density 0.323%

code-related commands and syntax in programming contexts

File paths and directories

project file paths

No Comments

No Known Activations