INDEX

Explanations

the presence of articles and specific counts related to subjects or objects

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

"A" or "an" followed by a noun

np_acts-logits-general · gemini-2.0-flash

a/an followed by a noun

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

BeginInit

-0.79

 asemenea

-0.73

ⓧ

-0.70

ItemBackground

-0.70

TypedDataSet

-0.67

DockStyle

-0.67

 Réponses

-0.66

 Agamemnon

-0.64

 Roskov

-0.64

 venuto

-0.62

POSITIVE LOGITS

 trio

0.60

 unnamed

0.56

 series

0.56

 pair

0.53

 recent

0.51

 branch

0.51

pano

0.51

/$',

0.50

 four

0.50

()?;

0.50

Activations Density 0.492%

the presence of articles and specific counts related to subjects or objects

"A" or "an" followed by a noun

a/an followed by a noun

No Comments

No Known Activations