INDEX

Explanations

URLs and code snippets, possibly related to website development

oai_token-act-pair · gemini-2.0-flash

Code/Programming

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

ré

-0.57

am

-0.56

-0.54

sur

-0.53

-0.51

-0.50

 care

-0.49

 pure

-0.48

in

-0.48

non

-0.47

POSITIVE LOGITS

 myſelf

0.93

ValueStyle

0.84

 itſelf

0.83

 purpoſe

0.82

Sucesor

0.81

 ſtate

0.81

__":

0.81

 pleaſure

0.80

__':

0.79

 Amadeus

0.79

Activations Density 1.479%

URLs and code snippets, possibly related to website development

Code/Programming

No Comments

No Known Activations