INDEX

Explanations

phrases and questions related to mathematical calculations, specifically around computing greatest common factors or divisors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/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.6.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

 semp

-0.49

 Vorbe

-0.47

 Choice

-0.43

ന്ന

-0.42

ruptcy

-0.40

assumption

-0.40

εί

-0.39

ாள

-0.39

lamos

-0.39

WhiteSpace

-0.39

POSITIVE LOGITS

 '\\;'

0.96

 calculate

0.95

 calculating

0.94

 Calcul

0.92

 referenties

0.89

ính

0.88

Calcul

0.88

 berech

0.86

 calculates

0.86

Calculate

0.86

Activations Density 0.676%

phrases and questions related to mathematical calculations, specifically around computing greatest common factors or divisors

No Comments

No Known Activations