INDEX

Explanations

words related to presentations, speakers, and lecturing

oai_token-act-pair · gemini-2.0-flash

speech, presentation

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

 <>",

-0.51

__);

-0.51

 getAccount

-0.49

 neceff

-0.49

#![

-0.48

 itſelf

-0.48

 raiſ

-0.47

 Römer

-0.47

 ſeveral

-0.47

 slurry

-0.47

POSITIVE LOGITS

WireFormatLite

0.66

XmlAccessType

0.64

 发表于

0.63

<bos>

0.62

apimachinery

0.60

 урна

0.56

żesz

0.55

FXMLLoader

0.54

 Roskov

0.54

 CreateTagHelper

0.53

Activations Density 25.426%

words related to presentations, speakers, and lecturing

speech, presentation

No Comments

No Known Activations