INDEX

Explanations

concepts related to adaptation and transfer learning in neural networks

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

trained tasks adaptation transferability

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

ModelAdmin

-0.43

findpost

-0.43

 autorytatywna

-0.41

EDEFAULT

-0.41

pannt

-0.41

Gu

-0.40

kriv

-0.39

car

-0.39

 chair

-0.38

astify

-0.38

POSITIVE LOGITS

TagMode

0.49

astéroïdes

0.48

RectangleBorder

0.47

UnknownFieldSet

0.46

Portail

0.43

ßerdem

0.41

----</

0.41

 Majesté

0.40

 whiteColor

0.40

oredCriteria

0.39

Activations Density 0.029%

concepts related to adaptation and transfer learning in neural networks

trained tasks adaptation transferability

No Comments

No Known Activations