INDEX

Explanations

technical terms related to media and audio sessions

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

connection policies

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

WithIOException

-0.52

BufferException

-0.41

Попис

-0.39

 hObject

-0.37

圣节

-0.36

Efq

-0.35

 MaterialApp

-0.34

 SqlParameter

-0.33

mbggenerated

-0.33

aho

-0.32

POSITIVE LOGITS

ImageContext

0.58

Lähteet

0.53

getColumnIndex

0.53

chability

0.52

 politiques

0.52

getSystemService

0.52

 autorytatywna

0.50

 Connectivity

0.48

Connectivity

0.47

 beweging

0.47

Activations Density 0.003%

technical terms related to media and audio sessions

connection policies

No Comments

No Known Activations