INDEX

Explanations

notes or annotations in the text

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

"Note" or "Notes"

np_acts-logits-general · gemini-2.0-flash

introducing a note

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

 DriverManager

-0.66

ętr

-0.64

最快更新

-0.59

 فريبيس

-0.59

หวัด

-0.57

martre

-0.57

missie

-0.56

щита

-0.56

scrollTop

-0.55

PositiveButton

-0.55

POSITIVE LOGITS

 notes

1.18

 Notes

1.14

Notes

1.00

 note

0.95

 Note

0.93

 NOTE

0.91

 NOTES

0.90

worthy

0.87

notes

0.86

Note

0.85

Activations Density 0.080%

notes or annotations in the text

"Note" or "Notes"

introducing a note

No Comments

No Known Activations