INDEX

Explanations

repetitions of the phrase "a lot."

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

"lot of" or "lots of"

np_acts-logits-general · gemini-2.0-flash

a lot of

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

 تضيفلها

-0.77

AnchorStyles

-0.76

 OnTriggerEnter

-0.75

 AssemblyCompany

-0.74

ReusableCell

-0.73

 MainAxisSize

-0.70

 insufficiency

-0.69

 limitless

-0.69

 Diſ

-0.69

 nucleon

-0.68

POSITIVE LOGITS

lot

0.92

Lot

0.80

Lot

0.76

LOT

0.72

 lots

0.67

LOT

0.66

of

0.65

 more

0.65

########.

0.63

teries

0.62

Activations Density 0.053%

repetitions of the phrase "a lot."

"lot of" or "lots of"

a lot of

No Comments

No Known Activations