INDEX

Explanations

code-related syntax and structure elements, particularly those related to functions and methods

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

Programming code comments/special characters

np_acts-logits-general · gemini-2.0-flash

code comments and keywords

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 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

uxxxx

-0.93

parsedMessage

-0.78

EndProject

-0.71

Tembelea

-0.67

addCriterion

-0.66

 '\\;'

-0.65

EndInit

-0.65

RegressionTest

-0.64

IntoConstraints

-0.63

Personendaten

-0.63

POSITIVE LOGITS

 Note

0.37

Glej

0.36

 limitée

0.36

botines

0.36

 farlo

0.36

IE

0.36

 This

0.36

værende

0.36

arbeit

0.35

 обычно

0.35

Activations Density 0.219%

code-related syntax and structure elements, particularly those related to functions and methods

Programming code comments/special characters

code comments and keywords

No Comments

No Known Activations