INDEX

Explanations

instances of reported speech or quotations in the text

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

attribution of quotes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

 betweenstory

-0.72

 CreateTagHelper

-0.41

原始内容存档于

-0.40

 hObject

-0.39

 الحره

-0.38

withstanding

-0.37

 EconPapers

-0.36

WebServlet

-0.35

 face

-0.35

findpost

-0.34

POSITIVE LOGITS

 propOrder

0.59

MessageTagHelper

0.57

 avoient

0.47

 Specifies

0.47

蚪

0.45

 Exacts

0.43

曖昧さ回避

0.43

FunctionFlags

0.43

paravant

0.42

Jeografia

0.42

Activations Density 0.017%

instances of reported speech or quotations in the text

attribution of quotes

No Comments

No Known Activations