INDEX

Explanations

technical terms and measurements related to biology and physics

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

biases of, DNA, fat, oil, blur

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

 resourceCulture

-0.34

noons

-0.34

 EClass

-0.32

 podjela

-0.31

/***/

-0.31

okości

-0.31

actoring

-0.31

 Italijani

-0.31

EndContext

-0.30

༘

-0.30

POSITIVE LOGITS

Personensuche

0.63

出版年

0.62

 otomatig

0.58

 queſta

0.57

 Vikipedi

0.57

المناصب

0.57

istoitu

0.56

رشف

0.54

 NSCoder

0.52

Referències

0.50

Activations Density 0.291%

technical terms and measurements related to biology and physics

biases of, DNA, fat, oil, blur

No Comments

No Known Activations