INDEX

Explanations

comments and annotations related to auto-generated code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

ScopeManager

-0.68

Parcelize

-0.60

 linkovi

-0.57

+:+

-0.56

lastonbury

-0.56

 TextInputType

-0.56

Населення

-0.55

 EnglishChoose

-0.54

 itemprop

-0.54

 jadx

-0.54

POSITIVE LOGITS

generated

0.88

IGENCE

0.68

Попис

0.63

 RemoteException

0.60

RegistryLite

0.58

tské

0.58

OGND

0.57

цездатний

0.57

ativement

0.57

subpackage

0.56

Activations Density 0.020%

comments and annotations related to auto-generated code

No Comments

No Known Activations