INDEX

Explanations

programming and software development terminology

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

import statements, code blocks

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-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

 NSCoder

-0.64

الدراسه

-0.55

endregion

-0.54

EClass

-0.54

 StatelessWidget

-0.54

SpringBootTest

-0.52

 ChromeDriver

-0.52

InjectAttribute

-0.52

ChromeDriver

-0.51

-------

-0.50

POSITIVE LOGITS

 AssemblyCulture

0.54

AddTagHelper

0.47

Халык

0.47

Бахар

0.46

PreferredItem

0.44

ſchen

0.43

Autoritní

0.42

ollary

0.41

guruan

0.40

jsdelivr

0.40

Activations Density 0.009%

programming and software development terminology

import statements, code blocks

No Comments

No Known Activations