INDEX

Explanations

references to model loading and saving operations in machine learning frameworks

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

Saving and loading models/weights

np_acts-logits-general · gemini-2.0-flash

model loading and saving

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

SPJ

-0.48

 Divi

-0.47

 Fermi

-0.46

 Ando

-0.45

quelize

-0.45

äiv

-0.45

ческом

-0.44

uanto

-0.43

 ActionBar

-0.43

foc

-0.42

POSITIVE LOGITS

 estekak

0.89

 weights

0.77

Referencie

0.69

stateProvider

0.69

XmlAccessType

0.67

DockStyle

0.66

enumi

0.63

InitVars

0.63

 BoxFit

0.62

 ويكيپيديا

0.59

Activations Density 0.154%

references to model loading and saving operations in machine learning frameworks

Saving and loading models/weights

model loading and saving

No Comments

No Known Activations