INDEX

Explanations

words and short phrases from a language other than English about confirming codes and agreements

oai_token-act-pair · gemini-2.0-flash

vr

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

期刊论文

-0.78

 ImportError

-0.77

 nahilalakip

-0.76

ագրություններ

-0.72

DockStyle

-0.68

 chi̍t

-0.66

hasMoreElements

-0.65

 resourceCulture

-0.63

)];

-0.63

featureID

-0.62

POSITIVE LOGITS

 confirm

1.38

 confirmation

1.35

 confirms

1.30

 confirming

1.30

 confirmed

1.30

 Confirm

1.24

Confirm

1.23

 confirmations

1.20

confirm

1.19

 verifies

1.16

Activations Density 0.597%

words and short phrases from a language other than English about confirming codes and agreements

vr

No Comments

No Known Activations