INDEX

Explanations

formal mathematical expressions and terminology related to proofs and theorems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.40.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

 ModelExpression

-0.59

 ujednoznacz

-0.52

发表于

-0.49

 término

-0.48

ագրություններ

-0.47

WithIOException

-0.47

 termes

-0.46

 Terms

-0.46

 TERMS

-0.45

Terms

-0.44

POSITIVE LOGITS

 principle

0.57

Principle

0.56

 Principle

0.52

principle

0.52

 continuity

0.51

 properties

0.50

 conservation

0.50

 principles

0.49

 invariance

0.47

 property

0.47

Activations Density 2.013%

formal mathematical expressions and terminology related to proofs and theorems

No Comments

No Known Activations