INDEX

Explanations

the word "paper" or actions related to writing

oai_token-act-pair · gemini-2.0-flash

say "paper"

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 Paper

-2.66

Paper

-2.63

 paper

-2.61

paper

-2.53

 papers

-2.47

 PAPER

-2.41

 Papers

-2.30

PAPER

-2.27

Papers

-2.19

papers

-2.16

POSITIVE LOGITS



0.54

 Brito

0.51

expandindo

0.50

存于互联网档案馆

0.47

gogo

0.47

 autorytatywna

0.46

 silvestre

0.46

шкан

0.46

onsored

0.46

 censiti

0.45

Activations Density 3.367%

the word "paper" or actions related to writing

say "paper"

No Comments

No Known Activations

the word "paper" or actions related to writing

say "paper"

No Comments

No Known Activations