INDEX

Explanations

technical terms and references related to programming or coding, particularly in the context of online account management

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

Non-English text or code

np_acts-logits-general · gemini-2.0-flash

Sloven before drug

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

 Meksiku

-0.54

ênis

-0.49

Javadoc

-0.49

'],$

-0.48

Cau

-0.48

Espèce

-0.47

 nije

-0.47

wh

-0.47

pannt

-0.46

nodoc

-0.46

POSITIVE LOGITS

شهاد

0.52

antaranya

0.51

 uska

0.50

copg

0.50

IntoConstraints

0.50

 verwijzen

0.49

»:

0.49

 unittest

0.49

 antaranya

0.48

self

0.48

Activations Density 0.055%

technical terms and references related to programming or coding, particularly in the context of online account management

Non-English text or code

Sloven before drug

No Comments

No Known Activations