INDEX

Explanations

references to data usage and its implications

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

concepts of interaction

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

principalColumn

-0.60

 sekal

-0.51

 pelúcia

-0.50

 fleste

-0.49

 kandang

-0.47

 elkaar

-0.46

 oprot

-0.46

 fidèles

-0.46

 fidèle

-0.46

 skolen

-0.45

POSITIVE LOGITS

tonode

0.63

XmlAccessType

0.62

 يتيمه

0.48

 transférez

0.47

 attacks

0.46

 Italijani

0.46

 issues

0.43

 analy

0.43

如何

0.40

Népesség

0.40

Activations Density 0.064%

references to data usage and its implications

concepts of interaction

No Comments

No Known Activations