INDEX

Explanations

mathematical symbols and variables used in equations and formulas

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

Code-related tokens

np_acts-logits-general · gemini-2.0-flash

GitHub repository names

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

RenderAtEndOf

-0.71

 Paglinawan

-0.61

 חיצוניים

-0.59

 EconPapers

-0.59

RegressionTest

-0.57

 المعيارى

-0.57

 ویکی‌پدیای

-0.56

клопе

-0.56

AndroidJUnit

-0.55

 informée

-0.52

POSITIVE LOGITS

 onAnimation

0.44

 both

0.42

 begge

0.40

oporosis

0.38

 CURLOPT

0.37

どちらも

0.36

 hiszen

0.35

 Jonas

0.34

 vixion

0.34

TODO

0.34

Activations Density 1.087%

mathematical symbols and variables used in equations and formulas

Code-related tokens

GitHub repository names

No Comments

No Known Activations