INDEX

Explanations

references to academic papers and structured information in citations

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

citation numbers and structural elements

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-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

出版年

-0.56

XmlAccessType

-0.52

 ModelExpression

-0.52

 oprot

-0.51

 CreateTagHelper

-0.48

dafx

-0.45

sim

-0.45

 apostolic

-0.44

 cune

-0.44

BufferException

-0.43

POSITIVE LOGITS

قایناق‌لار

0.44

 Accesat

0.40

قایناقلار

0.40

 tumbuh

0.39

 meminta

0.38

elesaikan

0.36

 satunya

0.36

ⓧ

0.36

 ועל

0.36

Demikian

0.36

Activations Density 0.176%

references to academic papers and structured information in citations

citation numbers and structural elements

No Comments

No Known Activations