INDEX

Explanations

programming syntax and language constructs

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

Code-related punctuation

np_acts-logits-general · gemini-2.0-flash

code comments and parameters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 otomatig

-0.70

 OMIT

-0.52

InitVars

-0.51

 препратки

-0.50

NDR

-0.49

 alternates

-0.48

GOTREF

-0.47

makeConstraints

-0.47

béco

-0.47

onAttach

-0.46

POSITIVE LOGITS

 års

0.38

 Dostupné

0.38

apimachinery

0.36

 ProtoMessage

0.35

localScale

0.35

 nahilalakip

0.34

InteropServices

0.34

closePath

0.32

roek

0.32

 MediatR

0.32

Activations Density 0.771%

programming syntax and language constructs

Code-related punctuation

code comments and parameters

No Comments

No Known Activations