INDEX

Explanations

the word "to"

oai_token-act-pair · gemini-2.0-flash

to

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

<bos>

-1.73

to

-1.09

’

-0.68

-0.63

httphttps

-0.56

‘

-0.49

']->

-0.49

larım

-0.48

If

-0.47

to

-0.47

POSITIVE LOGITS

MessageTagHelper

0.91

 censiti

0.73

 TestBed

0.69

 holotype

0.68

 tantum

0.64

 "..\..\

0.63

 alman

0.63

 propOrder

0.62

 chopsticks

0.61

featureID

0.61

Activations Density 2.655%

the word "to"

to

No Comments

No Known Activations