INDEX

Explanations

theorems and results related to mathematical proofs and properties

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 16-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

gypti

-0.47

idane

-0.45

越

-0.45

 Bedürfn

-0.44

ymce

-0.44

rowse

-0.42

Quiénes

-0.42

);*/

-0.42

 Platte

-0.41

mordial

-0.41

POSITIVE LOGITS

Theorem

0.92

 Theorem

0.86

 theorem

0.86

theorem

0.75

 theorems

0.74

THEOREM

0.74

Corollary

0.67

RegressionTest

0.66

 Theorems

0.64

Lemma

0.61

Activations Density 0.542%

theorems and results related to mathematical proofs and properties

No Comments

No Known Activations

theorems and results related to mathematical proofs and properties

No Comments

No Known Activations