INDEX

Explanations

terms related to acceleration and accelerometers

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 needs

-0.74

ervlak

-0.72

didSet

-0.71

 NEEDS

-0.69

needs

-0.68

 púb

-0.68

sety

-0.67

 Winaray

-0.67

 пои

-0.67

AdapterView

-0.66

POSITIVE LOGITS

 acceleration

1.16

 accelerate

1.04

 accelerates

1.03

 Acceleration

1.02

acceler

1.02

Acceler

0.97

 accelerating

0.93

ELER

0.91

acceleration

0.91

Acceleration

0.91

Activations Density 0.071%

terms related to acceleration and accelerometers

No Comments

No Known Activations