INDEX

Explanations

mentions of addresses in various contexts

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

"address" and related terms

np_acts-logits-general · gemini-2.0-flash

address or requirement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

coaster

-0.68

EndInit

-0.65

Anhalt

-0.62

phrine

-0.62

Према

-0.62

RLock

-0.60

AccessException

-0.60

herald

-0.58

ContentAsync

-0.58

 Weldon

-0.58

POSITIVE LOGITS

 getAddress

0.94

 Addresses

0.94

addresses

0.87

Addresses

0.85

 addresses

0.80

 ADDRESS

0.76

 地址

0.76

ograph

0.76

able

0.74

 addr

0.67

Activations Density 0.041%

mentions of addresses in various contexts

"address" and related terms

address or requirement

No Known Activations