INDEX

Explanations

the word "at"

oai_token-act-pair · gemini-2.0-flash

at

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

at

-3.20

 tại

-1.27

at

-1.13

in

-1.02

At

-0.93

bei

-0.84

At

-0.80

ở

-0.77

as

-0.75

-0.74

POSITIVE LOGITS

 Monfieur

1.23

 Theſe

1.16

Efq

1.05

 myſelf

1.01

 Cæsar

1.00

 becauſe

0.95

 itſelf

0.95

 pleaſure

0.94

 himſelf

0.90

 fevere

0.89

Activations Density 0.954%

the word "at"

at

No Comments

No Known Activations