INDEX

Explanations

references to feedback and its mechanisms

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

"feedback"

np_acts-logits-general · gemini-2.0-flash

feedback

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

mobileqq

-0.41



-0.39

richTextPanel

-0.39

mybatisplus

-0.39

PageFactory

-0.38

셈

-0.38

 Morg

-0.36

程度上

-0.36

 astore

-0.35

 Dism

-0.35

POSITIVE LOGITS

 feedback

2.61

 Feedback

2.42

Feedback

2.38

feedback

2.31

 FEEDBACK

2.11

 feedbacks

1.92

FEEDBACK

1.90

反馈

1.65

edback

1.44

 feed

0.95

Activations Density 0.136%

references to feedback and its mechanisms

"feedback"

feedback

No Comments

No Known Activations