INDEX

Explanations

mathematical terms and symbols related to functions and their properties in the context of mathematical proofs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

…

-0.55

ORTH

-0.52

 Eleven

-0.50

udah

-0.50

++){

-0.50

Am

-0.49

opis

-0.49

υμ

-0.49

...

-0.49

Sé

-0.49

POSITIVE LOGITS

 everywhere

0.88

iff

0.81

everywhere

0.77

 ovunque

0.74

 feroit

0.73

 térmico

0.69

 partout

0.69

@[+][

0.68

 vettoriale

0.68

 whenever

0.68

Activations Density 1.214%

mathematical terms and symbols related to functions and their properties in the context of mathematical proofs

No Comments

No Known Activations