INDEX

Explanations

conditional phrases, particularly those expressing possibility or potential

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

Sentences containing "could"

np_acts-logits-general · gemini-2.0-flash

expressing possibility or hypothetical situations

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

BOP

-0.72

’”

-0.72

 Lulu

-0.67

 跳转至

-0.66

”

-0.64

 Menge

-0.64

?”

-0.63

una

-0.63

“

-0.63

PreferredItem

-0.63

POSITIVE LOGITS

 conceivably

0.90

 COULD

0.89

could

0.83

'));

0.83

 Could

0.83

 could

0.79

 poderia

0.79

Sre

0.78

Could

0.78

 potentially

0.75

Activations Density 0.094%

conditional phrases, particularly those expressing possibility or potential

Sentences containing "could"

expressing possibility or hypothetical situations

No Comments

No Known Activations