INDEX

Explanations

function definitions and calls in code

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

Code following functions-related tokens (like "toEqual", "Line", "tuple")

np_acts-logits-general · gemini-2.0-flash

identifier followed by punctuation

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

 theirs

-1.76

 mine

-1.67

 yours

-1.62

 hers

-1.57

 ours

-1.57

Mine

-1.49

 Mine

-1.45

 Yours

-1.39

mine

-1.34

 MINE

-1.32

POSITIVE LOGITS

 disponibilités

0.60

PerformLayout

0.57

EditorBrowsable

0.54

irchen

0.54

 Wicidata

0.49

rogels

0.49

estias

0.48

]")]

0.48

WebServlet

0.47

RenderAtEndOf

0.46

Activations Density 0.398%

function definitions and calls in code

Code following functions-related tokens (like "toEqual", "Line", "tuple")

identifier followed by punctuation

No Comments

No Known Activations