INDEX

Explanations

abstract concepts possibly relating to martial arts due to terms like "tai chi" and "martial way".

oai_token-act-pair · gemini-2.0-flash

programming or technical terms

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

code and foreign words

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

 endblock

-0.63

 arrang

-0.49

lež

-0.48

!*\

-0.47

 lips

-0.46

PLEX

-0.45

BrowserModule

-0.44

toi

-0.44

 дописавши

-0.44

odb

-0.43

POSITIVE LOGITS

دانشنامهٔ

0.63

 SqlCommand

0.63

elry

0.60

 >=",

0.60

reportWebVitals

0.57

elfare

0.57

 caen

0.56

 InputDecoration

0.53

 universale

0.52

SequentialGroup

0.52

Activations Density 1.194%

abstract concepts possibly relating to martial arts due to terms like "tai chi" and "martial way".

programming or technical terms

code and foreign words

No Comments

No Known Activations