INDEX

Explanations

mentions of using electronic devices and their associated features or capabilities.

oai_token-act-pair · gemini-2.0-flash

technical software-related terms

np_token-act-pair-logits · gpt-4o-mini

it

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 nahilalakip

-0.64

Personendaten

-0.60

dziew

-0.57

 שוליים

-0.53

 aidant

-0.52

原始内容存档于

-0.51

 fortsetter

-0.50

তথ্যসূত্র

-0.50

Клуб

-0.49

ագրություններ

-0.46

POSITIVE LOGITS

\{\\

0.62

TagMode

0.59

 resourceCulture

0.59

 intraven

0.58

WindowConstants

0.57

 ferv

0.54

#+#

0.54

erai

0.53

eakers

0.52

 faithfully

0.52

Activations Density 3.928%

mentions of using electronic devices and their associated features or capabilities.

technical software-related terms

it

No Comments

No Known Activations