INDEX

Explanations

words related to achieving goals in a learning environment

oai_token-act-pair · gemini-2.0-flash

terms related to programming or technical concepts

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

technical instructions and code

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

 espiral

-0.50

 rând

-0.49

 tartalomajánló

-0.49

 فريبيس

-0.47

TID

-0.46

thou

-0.46

entibus

-0.44

 débats

-0.44

 extérieures

-0.44

 bénéfices

-0.44

POSITIVE LOGITS

SequentialGroup

0.77

photobucket

0.77

makeConstraints

0.63

 BrowserModule

0.63

igslist

0.63

сторія

0.60

ynchronously

0.58

 كومونز

0.58

PostConstruct

0.57

HtmlAttribute

0.56

Activations Density 0.571%

words related to achieving goals in a learning environment

terms related to programming or technical concepts

technical instructions and code

No Comments

No Known Activations