INDEX

Explanations

a mix of code snippets, mathematical symbols, and computer-related terms.

oai_token-act-pair · gemini-2.0-flash

code

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

webElementXpaths

-0.70

 kasarigan

-0.67

GEBURTSDATUM

-0.58

:✨

-0.57

 Numerade

-0.54

WriteBarrier

-0.54

 himo

-0.53

دانشنامهٔ

-0.53

 Wikimedijinoj

-0.53

memoized

-0.52

POSITIVE LOGITS

HomeAsUpEnabled

0.59

mybatisplus

0.56

MLLoader

0.54

hals

0.54

topus

0.53

EMOS

0.52

KommentareTeilen

0.52

omini

0.51

DockStyle

0.50

CrossRef

0.50

Activations Density 3.357%

a mix of code snippets, mathematical symbols, and computer-related terms.

code

No Comments

No Known Activations