INDEX

Explanations

words and phrases related to product reviews and specifications, as well as some location-based terms

oai_token-act-pair · gemini-2.0-flash

Citation context

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 autorytatywna

-0.59

 &___

-0.53

 nahilalakip

-0.48

 endwhile

-0.48

crollView

-0.47

Jop

-0.46

//

-0.46

 esternos

-0.45

CppMethod

-0.44

InjectAttribute

-0.44

POSITIVE LOGITS

ConstraintMaker

0.60

 оригіналу

0.60

EndGlobalSection

0.56

ⓧ

0.56

 Cast

0.54

 Porta

0.53

ارات

0.52

 ComVisible

0.52

tinyos

0.52

Cast

0.51

Activations Density 2.440%

words and phrases related to product reviews and specifications, as well as some location-based terms

Citation context

No Comments

No Known Activations