INDEX

Explanations

phrases related to the negative consequences of an action

oai_token-act-pair · gemini-2.0-flash

cost and expense

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Enllaces

-0.63

)++;

-0.58

 disponibilités

-0.58

Efq

-0.57

UIControlState

-0.52

esez

-0.52

xFFFFFF

-0.52

twimg

-0.52

 препратки

-0.52

openConnection

-0.51

POSITIVE LOGITS

at

1.57

 expense

1.38

At

1.08

 Expense

1.04

expense

1.04

At

0.99

 cost

0.99

at

0.94

 expenses

0.89

 Cost

0.88

Activations Density 1.016%

phrases related to the negative consequences of an action

cost and expense

No Comments

No Known Activations