INDEX

Explanations

the word "browser".

oai_token-act-pair · gemini-2.0-flash

browser

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

Not in Any Lists

No Comments

Negative Logits

and

-0.93

in

-0.85

or

-0.82

can

-0.80

the

-0.78

be

-0.77

at

-0.77

 total

-0.74

POSITIVE LOGITS

Efq

1.37

 pleaſure

1.33

 Monfieur

1.33

 Shakspeare

1.33

 myſelf

1.30

 CreateTagHelper

1.29

 Theſe

1.29

 Reſ

1.26

 purpoſe

1.25

 Jefus

1.23

Activations Density 0.440%

the word "browser".

browser

No Comments

No Known Activations