INDEX

Explanations

technical terms and tools related to software configuration and management

oai_token-act-pair · gpt-4o-mini Triggered by @bot

programmes, workshops, run

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

GEBURTS

-0.58

 GenerationType

-0.50

XmlType

-0.50

хьтан

-0.48

 ویکی‌پدی

-0.47

MemoryWarning

-0.47

 ModelExpression

-0.47

SourceChecksum

-0.46

bootstrapcdn

-0.46

 nakalista

-0.46

POSITIVE LOGITS

__::

0.47

]=>

0.45

 workshops

0.41

WithError

0.40

 tool

0.40

pod

0.39

 workshop

0.39

 IFTT

0.38

 programme

0.38

run

0.37

Activations Density 0.071%

technical terms and tools related to software configuration and management

programmes, workshops, run

No Comments

No Known Activations