INDEX

Explanations

numerical values and potentially their relevance in a given context

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

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 avoient

-0.61

\{\\

-0.60

 étoient

-0.57

 feroit

-0.57

featureID

-0.57

 queſta

-0.57

 juſ

-0.57

fjspx

-0.55

})*/

-0.53

 BaseController

-0.53

POSITIVE LOGITS

 وتسجيلات

0.39

----</

0.38

Ɓ

0.35

eqnarray

0.34

nezeu

0.31

Contact

0.28

Ͳ

0.28

 piacere

0.27

 Contact

0.27

jgl

0.27

Activations Density 0.231%

numerical values and potentially their relevance in a given context

No Comments

No Known Activations