INDEX

Explanations

instances of the prefix "de-," particularly in words indicating removal or reversal

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

starting with "de" followed by a consonant

np_acts-logits-general · gemini-2.0-flash

starts with de

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

примеча

-0.65

SuccessListener

-0.60

writerow

-0.55

vemos

-0.53

QPalette

-0.51

ertale

-0.51

MENAFN

-0.51

__":

-0.51

Efq

-0.51

ResponseWriter

-0.51

POSITIVE LOGITS

 cherchés

0.56

XmlAccessorType

0.50

={`/

0.47

writeFieldEnd

0.47

folg

0.46

dine

0.46

construct

0.45

construction

0.44

 miatt

0.41

={[

0.41

Activations Density 0.139%

instances of the prefix "de-," particularly in words indicating removal or reversal

starting with "de" followed by a consonant

starts with de

No Comments

No Known Activations