INDEX

Explanations

the word "address" in different contexts

oai_token-act-pair · gemini-2.0-flash

address

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

 address

-1.59

address

-1.21

 addressing

-1.10

Address

-1.09

 Address

-1.03

<bos>

-0.99

 addresses

-0.96

 addressed

-0.90

 ADDRESS

-0.78

-0.76

POSITIVE LOGITS

URLException

1.42

ymce

1.18

TagMode

1.16

 InputDecoration

1.13

AxisAlignment

1.11

zzleHttp

1.10

 AssemblyVersion

1.08

endpush

1.05

principalColumn

1.04

Portail

1.03

Activations Density 0.829%

the word "address" in different contexts

address

No Known Activations