INDEX

Explanations

expressions related to levels and changes in biological attributes or parameters

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

abundance or high quantity

np_acts-logits-general · gemini-2.0-flash

high expression, low quantity

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

UserScript

-0.57

 disambiguazione

-0.53

DispatchToProps

-0.51

 FetchType

-0.50

الحياه

-0.50

 lenker

-0.47

ErrUnexpectedEOF

-0.46

})();

-0.46

AndEndTag

-0.46



-0.46

POSITIVE LOGITS

 henceforth

0.38

Geplaatst

0.38

AddHtmlAttribute

0.36

ignements

0.36

stdc

0.35

忑

0.34

 öss

0.34

êques

0.34

 Drucker

0.33

 ouder

0.33

Activations Density 1.255%

expressions related to levels and changes in biological attributes or parameters

abundance or high quantity

high expression, low quantity

No Comments

No Known Activations