INDEX

Explanations

references to debugging processes and tools

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

Debugging or troubleshooting

np_acts-logits-general · gemini-2.0-flash

debugging and stepping

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

Obrázky

-0.60

complexType

-0.54

Initializable

-0.54

 Malo

-0.51

 nahilalakip

-0.50

complexContent

-0.49

Composable

-0.48

 nonatomic

-0.46

upol

-0.46

ส์

-0.46

POSITIVE LOGITS

 debug

1.79

 debugging

1.71

debug

1.57

 Debug

1.57

Debug

1.48

 Debugging

1.43

 debugger

1.39

 trace

1.34

 DEBUG

1.28

Debugging

1.27

Activations Density 0.767%

references to debugging processes and tools

Debugging or troubleshooting

debugging and stepping

No Comments

No Known Activations