INDEX

Explanations

uses of the words "as", "shown" or "can" that occur near each other

oai_token-act-pair · gemini-2.0-flash

As

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 thèmes

-0.54

amarin

-0.52

 sẻ

-0.51

蚪

-0.50

elter

-0.50

enumi

-0.47

HeaderText

-0.47

 nuages

-0.47

Anonymous

-0.47

fering

-0.46

POSITIVE LOGITS

 before

0.85

before

0.66

 sebelum

0.61

 Before

0.59

Sebelum

0.59

 bevor

0.57

 før

0.57

 Sebelum

0.57

Antes

0.56

 voordat

0.55

Activations Density 4.933%

uses of the words "as", "shown" or "can" that occur near each other

As

No Comments

No Known Activations