INDEX

Explanations

sentences that include the word "Note" or similar variations, indicating important information or references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 quelcon

-0.49

 pelúcia

-0.46

 isEmpty

-0.46

 McAllister

-0.46

ְׁ

-0.45

azi

-0.45

 garagem

-0.44

 Christiansen

-0.44

 européennes

-0.44

 ChromeDriver

-0.44

POSITIVE LOGITS

 note

1.21

 Note

1.13

 Notes

1.07

 notes

1.07

Note

1.05

note

1.02

Notes

0.98

 NOTES

0.93

 noted

0.91

notes

0.91

Activations Density 0.152%

sentences that include the word "Note" or similar variations, indicating important information or references

No Comments

No Known Activations