INDEX

Explanations

code snippets, especially Java code involving configuration and socket parameters.

oai_token-act-pair · gemini-2.0-flash

programming-related terminology

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

Code related contexts

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

хьтан

-0.42

OGND

-0.40

 OMITBAD

-0.39

---|---|

-0.38

 khoản

-0.35

المشاركات

-0.35

 kaarangay

-0.34

 Staff

-0.34

ums

-0.34

nitte

-0.34

POSITIVE LOGITS

 disponibilités

0.73

ⓧ

0.69

NameInMap

0.65

Portale

0.64

brica

0.64

WebServlet

0.63

ArgsConstructor

0.62

testify

0.62

Vidite

0.61

habad

0.61

Activations Density 2.787%

code snippets, especially Java code involving configuration and socket parameters.

programming-related terminology

Code related contexts

No Comments

No Known Activations