INDEX

Explanations

expressions of possibility or uncertainty

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

"Might" followed by a verb

np_acts-logits-general · gemini-2.0-flash

indicating possibility

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

SBATCH

-0.71

ear

-0.64

 Peres

-0.64

قایناقلار

-0.62

Controllo

-0.62

AndEndTag

-0.61

 springfox

-0.61

UMBIA

-0.61

 Breen

-0.60

er

-0.60

POSITIVE LOGITS

ally

0.85

ViewFeatures

0.70

GeoNames

0.69

 conceivably

0.67

Ehh

0.66

————————

0.66

ALLY

0.64

 MIGHT

0.64

ity

0.63

Moi

0.63

Activations Density 0.064%

expressions of possibility or uncertainty

"Might" followed by a verb

indicating possibility

No Comments

No Known Activations